Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4808 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.4330. Min Act: -0.1700
Data Index: 342963 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.4017. Min Act: -0.1700
Data Index: 3431035 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.4017. Min Act: -0.1700
Data Index: 1333196 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.4017. Min Act: -0.1700
Data Index: 8232410 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.3860. Min Act: -0.1700
Data Index: 915794 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.3546. Min Act: -0.1700
Data Index: 6668177 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.3546. Min Act: -0.1700
Data Index: 5054675 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.3546. Min Act: -0.1700
Data Index: 1334863 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.3389. Min Act: -0.1700
Data Index: 4343197 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.3075. Min Act: -0.1700
Data Index: 3604229 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.3075. Min Act: -0.1700
Data Index: 435686 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.2918. Min Act: -0.1700
Data Index: 5536056 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.3075. Min Act: -0.1700
Data Index: 7493248 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.2918. Min Act: -0.1700
Data Index: 6256017 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.2761. Min Act: -0.1700
Data Index: 7998237 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.2604. Min Act: -0.1700
Data Index: 8590449 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.2604. Min Act: -0.1700
Data Index: 1874899 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.2604. Min Act: -0.1700
Data Index: 4189000 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.2604. Min Act: -0.1700
Data Index: 6303222 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4330. Min Range: -3.4330
Max Act: 3.2604. Min Act: -0.1700
Data Index: 6412880 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19