Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3809 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4571. Min Range: -5.4571
Max Act: 5.4571. Min Act: -0.1700
Data Index: 1093533 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4571. Min Range: -5.4571
Max Act: 5.2071. Min Act: -0.1700
Data Index: 646969 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4571. Min Range: -5.4571
Max Act: 5.0821. Min Act: -0.1700
Data Index: 746324 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4571. Min Range: -5.4571
Max Act: 5.0508. Min Act: -0.1700
Data Index: 1319787 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4571. Min Range: -5.4571
Max Act: 5.0508. Min Act: -0.1700
Data Index: 2381885 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4571. Min Range: -5.4571
Max Act: 5.0196. Min Act: -0.1700
Data Index: 3654229 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4571. Min Range: -5.4571
Max Act: 5.0196. Min Act: -0.1700
Data Index: 4113948 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4571. Min Range: -5.4571
Max Act: 5.0196. Min Act: -0.1700
Data Index: 6674903 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4571. Min Range: -5.4571
Max Act: 5.0196. Min Act: -0.1700
Data Index: 2859203 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4571. Min Range: -5.4571
Max Act: 4.9883. Min Act: -0.1700
Data Index: 1874575 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4571. Min Range: -5.4571
Max Act: 5.0196. Min Act: -0.1700
Data Index: 4732548 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4571. Min Range: -5.4571
Max Act: 4.9883. Min Act: -0.1700
Data Index: 3384424 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4571. Min Range: -5.4571
Max Act: 5.0196. Min Act: -0.1700
Data Index: 6548855 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4571. Min Range: -5.4571
Max Act: 4.9571. Min Act: -0.1700
Data Index: 6240625 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4571. Min Range: -5.4571
Max Act: 4.9571. Min Act: -0.1700
Data Index: 8161071 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4571. Min Range: -5.4571
Max Act: 4.9571. Min Act: -0.1700
Data Index: 3687785 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4571. Min Range: -5.4571
Max Act: 4.9258. Min Act: -0.1700
Data Index: 6156199 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4571. Min Range: -5.4571
Max Act: 4.8946. Min Act: -0.1700
Data Index: 5502581 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4571. Min Range: -5.4571
Max Act: 4.9258. Min Act: -0.1700
Data Index: 215203 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4571. Min Range: -5.4571
Max Act: 4.8946. Min Act: -0.1700
Data Index: 5466681 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19