Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4047 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.5841. Min Act: -0.1700
Data Index: 8042506 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.5841. Min Act: -0.1700
Data Index: 7187524 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.4432. Min Act: -0.1700
Data Index: 8566599 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.4432. Min Act: -0.1700
Data Index: 3891781 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.4118. Min Act: -0.1700
Data Index: 6778641 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.3962. Min Act: -0.1700
Data Index: 2828235 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.3962. Min Act: -0.1700
Data Index: 587038 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.3805. Min Act: -0.1700
Data Index: 1550439 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.3491. Min Act: -0.1700
Data Index: 1629517 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.2863. Min Act: -0.1700
Data Index: 4987520 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.2863. Min Act: -0.1700
Data Index: 8393744 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.2863. Min Act: -0.1700
Data Index: 7961761 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.2863. Min Act: -0.1700
Data Index: 2513169 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.3020. Min Act: -0.1700
Data Index: 441350 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.2078. Min Act: -0.1700
Data Index: 2580388 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.2235. Min Act: -0.1700
Data Index: 8488836 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.2235. Min Act: -0.1700
Data Index: 94868 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.2392. Min Act: -0.1700
Data Index: 3336801 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.2235. Min Act: -0.1700
Data Index: 7856247 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5841. Min Range: -3.5841
Max Act: 3.2078. Min Act: -0.1700
Data Index: 4849291 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19