Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2036 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.6149. Min Act: -0.1700
Data Index: 736793 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.5666. Min Act: -0.1700
Data Index: 7388190 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.5504. Min Act: -0.1700
Data Index: 2629004 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.5343. Min Act: -0.1700
Data Index: 6521452 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.5504. Min Act: -0.1700
Data Index: 4650085 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.5343. Min Act: -0.1700
Data Index: 5965182 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.5019. Min Act: -0.1700
Data Index: 1210928 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4857. Min Act: -0.1700
Data Index: 7710046 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4695. Min Act: -0.1700
Data Index: 4711991 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4695. Min Act: -0.1700
Data Index: 4589356 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4695. Min Act: -0.1700
Data Index: 2987449 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4695. Min Act: -0.1700
Data Index: 3475256 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4695. Min Act: -0.1700
Data Index: 3681673 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4532. Min Act: -0.1700
Data Index: 8645562 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4695. Min Act: -0.1700
Data Index: 156881 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4370. Min Act: -0.1700
Data Index: 1876798 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4370. Min Act: -0.1700
Data Index: 7398422 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4207. Min Act: -0.1700
Data Index: 151729 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4370. Min Act: -0.1700
Data Index: 3691410 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4370. Min Act: -0.1700
Data Index: 5063174 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19