Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.3007. Min Act: -0.1700
Data Index: 8068612 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.1592. Min Act: -0.1700
Data Index: 660629 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.1435. Min Act: -0.1700
Data Index: 732914 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0962. Min Act: -0.1700
Data Index: 2111489 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0805. Min Act: -0.1700
Data Index: 660630 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0805. Min Act: -0.1700
Data Index: 5076775 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0489. Min Act: -0.1700
Data Index: 4918550 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0647. Min Act: -0.1700
Data Index: 4118705 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0647. Min Act: -0.1700
Data Index: 4349844 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0331. Min Act: -0.1700
Data Index: 5933237 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0489. Min Act: -0.1700
Data Index: 3492136 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0331. Min Act: -0.1700
Data Index: 3473453 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0331. Min Act: -0.1700
Data Index: 2840018 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0331. Min Act: -0.1700
Data Index: 3768677 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0331. Min Act: -0.1700
Data Index: 1742899 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0489. Min Act: -0.1700
Data Index: 6576494 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0173. Min Act: -0.1700
Data Index: 2888465 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0015. Min Act: -0.1700
Data Index: 5035839 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0015. Min Act: -0.1700
Data Index: 2381749 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3007. Min Range: -3.3007
Max Act: 3.0173. Min Act: -0.1700
Data Index: 5099602 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19