Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1689. Min Range: -4.1689
Max Act: 4.1689. Min Act: -0.1700
Data Index: 8510580 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.9188. Min Act: -0.1700
Data Index: 8246138 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.8875. Min Act: -0.1700
Data Index: 5849486 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.9188. Min Act: -0.1700
Data Index: 5734492 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.8875. Min Act: -0.1700
Data Index: 5917834 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.8562. Min Act: -0.1700
Data Index: 1828518 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.8250. Min Act: -0.1700
Data Index: 7888197 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.8250. Min Act: -0.1700
Data Index: 3743518 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.8093. Min Act: -0.1700
Data Index: 1239184 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.7937. Min Act: -0.1700
Data Index: 2535719 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.7781. Min Act: -0.1700
Data Index: 7190534 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.7937. Min Act: -0.1700
Data Index: 5324082 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.8093. Min Act: -0.1700
Data Index: 604323 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.7937. Min Act: -0.1700
Data Index: 8113587 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.7781. Min Act: -0.1700
Data Index: 408082 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.7624. Min Act: -0.1700
Data Index: 1802185 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.7624. Min Act: -0.1700
Data Index: 8553509 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.7624. Min Act: -0.1700
Data Index: 7784823 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.7624. Min Act: -0.1700
Data Index: 3648281 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1689. Min Range: -4.1689
Max Act: 3.7468. Min Act: -0.1700
Data Index: 7127880 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19