Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3535 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.7554. Min Act: -0.1700
Data Index: 8536143 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.7085. Min Act: -0.1700
Data Index: 4133613 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.6772. Min Act: -0.1700
Data Index: 290372 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.6616. Min Act: -0.1700
Data Index: 6917751 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.6459. Min Act: -0.1700
Data Index: 432445 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.6303. Min Act: -0.1700
Data Index: 2019992 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.6459. Min Act: -0.1700
Data Index: 1618096 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.6459. Min Act: -0.1700
Data Index: 3281064 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.6303. Min Act: -0.1700
Data Index: 6134946 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.6303. Min Act: -0.1700
Data Index: 3603386 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5833. Min Act: -0.1700
Data Index: 8786983 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5677. Min Act: -0.1700
Data Index: 2213865 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5677. Min Act: -0.1700
Data Index: 5633942 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5990. Min Act: -0.1700
Data Index: 6475189 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5520. Min Act: -0.1700
Data Index: 8686358 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5520. Min Act: -0.1700
Data Index: 4214137 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5363. Min Act: -0.1700
Data Index: 3540469 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5520. Min Act: -0.1700
Data Index: 4746550 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5363. Min Act: -0.1700
Data Index: 166876 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5363. Min Act: -0.1700
Data Index: 7819619 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19