Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1784 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.4837. Min Act: -0.1700
Data Index: 6593320 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.5149. Min Act: -0.1700
Data Index: 2961318 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.4837. Min Act: -0.1700
Data Index: 3695778 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.4837. Min Act: -0.1700
Data Index: 5551929 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.4212. Min Act: -0.1700
Data Index: 569995 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.4212. Min Act: -0.1700
Data Index: 6549369 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.4212. Min Act: -0.1700
Data Index: 900246 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.4212. Min Act: -0.1700
Data Index: 2798323 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.3587. Min Act: -0.1700
Data Index: 3233828 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.3587. Min Act: -0.1700
Data Index: 6136826 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.3274. Min Act: -0.1700
Data Index: 7627775 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.3274. Min Act: -0.1700
Data Index: 8820056 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.3274. Min Act: -0.1700
Data Index: 4981389 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.3274. Min Act: -0.1700
Data Index: 854512 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.3274. Min Act: -0.1700
Data Index: 7701093 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.3274. Min Act: -0.1700
Data Index: 570876 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.2962. Min Act: -0.1700
Data Index: 297486 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.2962. Min Act: -0.1700
Data Index: 1041770 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.2962. Min Act: -0.1700
Data Index: 1877092 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5149. Min Range: -4.5149
Max Act: 4.2962. Min Act: -0.1700
Data Index: 42167 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19