Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1752 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.5469. Min Range: -11.5469
Max Act: 11.5469. Min Act: -0.1700
Data Index: 6158101 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5469. Min Range: -11.5469
Max Act: 11.4844. Min Act: -0.1700
Data Index: 6158098 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5469. Min Range: -11.5469
Max Act: 11.5469. Min Act: -0.1700
Data Index: 3796981 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5469. Min Range: -11.5469
Max Act: 11.5469. Min Act: -0.1700
Data Index: 6141360 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5469. Min Range: -11.5469
Max Act: 11.3594. Min Act: -0.1700
Data Index: 1385688 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5469. Min Range: -11.5469
Max Act: 11.1719. Min Act: -0.1700
Data Index: 750530 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.9844. Min Act: -0.1700
Data Index: 6792080 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.9219. Min Act: -0.1700
Data Index: 3805005 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.7969. Min Act: -0.1700
Data Index: 4564809 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.8594. Min Act: -0.1700
Data Index: 5747915 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.7969. Min Act: -0.1700
Data Index: 3691488 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.7969. Min Act: -0.1700
Data Index: 7626202 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.6719. Min Act: -0.1700
Data Index: 5449867 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.7344. Min Act: -0.1700
Data Index: 3805004 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.7344. Min Act: -0.1700
Data Index: 8337285 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.4844. Min Act: -0.1700
Data Index: 33135 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.4219. Min Act: -0.1700
Data Index: 3762476 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.3594. Min Act: -0.1700
Data Index: 3401942 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.4219. Min Act: -0.1700
Data Index: 1031691 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5469. Min Range: -11.5469
Max Act: 10.3594. Min Act: -0.1700
Data Index: 4232401 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19