Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.5886. Min Act: -0.1700
Data Index: 1026065 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.2761. Min Act: -0.1700
Data Index: 6058530 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.1511. Min Act: -0.1700
Data Index: 6165439 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.1511. Min Act: -0.1700
Data Index: 9643 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.1198. Min Act: -0.1700
Data Index: 3455422 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.1198. Min Act: -0.1700
Data Index: 449737 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.0886. Min Act: -0.1700
Data Index: 4853583 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.0886. Min Act: -0.1700
Data Index: 2131484 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.0886. Min Act: -0.1700
Data Index: 4503366 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.0261. Min Act: -0.1700
Data Index: 6055402 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.0886. Min Act: -0.1700
Data Index: 4025932 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.0261. Min Act: -0.1700
Data Index: 5324938 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.0261. Min Act: -0.1700
Data Index: 2115138 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5886. Min Range: -7.5886
Max Act: 6.9948. Min Act: -0.1700
Data Index: 956408 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5886. Min Range: -7.5886
Max Act: 6.9948. Min Act: -0.1700
Data Index: 1558352 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5886. Min Range: -7.5886
Max Act: 6.9323. Min Act: -0.1700
Data Index: 7705344 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5886. Min Range: -7.5886
Max Act: 6.9636. Min Act: -0.1700
Data Index: 5127493 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5886. Min Range: -7.5886
Max Act: 6.9948. Min Act: -0.1700
Data Index: 7348345 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5886. Min Range: -7.5886
Max Act: 7.0261. Min Act: -0.1700
Data Index: 1128586 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5886. Min Range: -7.5886
Max Act: 6.9636. Min Act: -0.1700
Data Index: 5505807 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19