Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1081 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0468. Min Range: -6.0468
Max Act: 6.0468. Min Act: -0.1700
Data Index: 7954572 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0468. Min Range: -6.0468
Max Act: 6.0468. Min Act: -0.1700
Data Index: 99339 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.9530. Min Act: -0.1700
Data Index: 6615089 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.9218. Min Act: -0.1700
Data Index: 1547862 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.9218. Min Act: -0.1700
Data Index: 8496736 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.9218. Min Act: -0.1700
Data Index: 3918277 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.8905. Min Act: -0.1700
Data Index: 7328932 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.8593. Min Act: -0.1700
Data Index: 8243640 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.8280. Min Act: -0.1700
Data Index: 5394135 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.7968. Min Act: -0.1700
Data Index: 7733841 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.7968. Min Act: -0.1700
Data Index: 8393156 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.7968. Min Act: -0.1700
Data Index: 4883697 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.7968. Min Act: -0.1700
Data Index: 8227466 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.7343. Min Act: -0.1700
Data Index: 4955000 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.7968. Min Act: -0.1700
Data Index: 7446381 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.7030. Min Act: -0.1700
Data Index: 6879844 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.7030. Min Act: -0.1700
Data Index: 8248712 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.7030. Min Act: -0.1700
Data Index: 6868243 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.7030. Min Act: -0.1700
Data Index: 4730756 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0468. Min Range: -6.0468
Max Act: 5.7030. Min Act: -0.1700
Data Index: 7772894 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19