Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2562 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.7396. Min Act: -0.1700
Data Index: 866784 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.7396. Min Act: -0.1700
Data Index: 2409986 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.6459. Min Act: -0.1700
Data Index: 1137848 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.6459. Min Act: -0.1700
Data Index: 8563607 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.6459. Min Act: -0.1700
Data Index: 5633369 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.6146. Min Act: -0.1700
Data Index: 6983109 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.6146. Min Act: -0.1700
Data Index: 276012 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.6146. Min Act: -0.1700
Data Index: 1898653 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5521. Min Act: -0.1700
Data Index: 2049435 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5521. Min Act: -0.1700
Data Index: 3304642 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5209. Min Act: -0.1700
Data Index: 8046006 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.4896. Min Act: -0.1700
Data Index: 2137425 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5521. Min Act: -0.1700
Data Index: 2228521 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5209. Min Act: -0.1700
Data Index: 3334633 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5209. Min Act: -0.1700
Data Index: 2137436 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5209. Min Act: -0.1700
Data Index: 5871118 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.4896. Min Act: -0.1700
Data Index: 1989231 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.4584. Min Act: -0.1700
Data Index: 877946 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.4896. Min Act: -0.1700
Data Index: 5164157 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.4271. Min Act: -0.1700
Data Index: 1780777 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19