Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.2826. Min Act: -0.1700
Data Index: 1638441 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.2826. Min Act: -0.1700
Data Index: 5732401 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.2662. Min Act: -0.1700
Data Index: 430418 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.2331. Min Act: -0.1700
Data Index: 5348099 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.2331. Min Act: -0.1700
Data Index: 5366227 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.2496. Min Act: -0.1700
Data Index: 3521784 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.2166. Min Act: -0.1700
Data Index: 8147282 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.2166. Min Act: -0.1700
Data Index: 3175229 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.2166. Min Act: -0.1700
Data Index: 7424854 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.2000. Min Act: -0.1700
Data Index: 6134821 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.2000. Min Act: -0.1700
Data Index: 6234249 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.2000. Min Act: -0.1700
Data Index: 6520942 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.1834. Min Act: -0.1700
Data Index: 1986739 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.2000. Min Act: -0.1700
Data Index: 5340366 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.1834. Min Act: -0.1700
Data Index: 1450593 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.1834. Min Act: -0.1700
Data Index: 6336423 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.1667. Min Act: -0.1700
Data Index: 949712 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.1667. Min Act: -0.1700
Data Index: 1870894 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.1667. Min Act: -0.1700
Data Index: 1694146 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2826. Min Range: -2.2826
Max Act: 2.1501. Min Act: -0.1700
Data Index: 445272 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19