Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1135. Min Range: -6.1135
Max Act: 6.1135. Min Act: -0.1700
Data Index: 7920135 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.6760. Min Act: -0.1700
Data Index: 618968 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.6447. Min Act: -0.1700
Data Index: 6161566 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.6760. Min Act: -0.1700
Data Index: 7034040 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.6135. Min Act: -0.1700
Data Index: 637671 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.5510. Min Act: -0.1700
Data Index: 938374 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.4572. Min Act: -0.1700
Data Index: 4715781 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.4260. Min Act: -0.1700
Data Index: 6289532 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.3947. Min Act: -0.1700
Data Index: 774472 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.3635. Min Act: -0.1700
Data Index: 4231475 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.3322. Min Act: -0.1700
Data Index: 2047188 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.3322. Min Act: -0.1700
Data Index: 6651439 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.3322. Min Act: -0.1700
Data Index: 1792334 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.2697. Min Act: -0.1700
Data Index: 6536059 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.3010. Min Act: -0.1700
Data Index: 7889975 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.2697. Min Act: -0.1700
Data Index: 3322394 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.2697. Min Act: -0.1700
Data Index: 131606 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.2697. Min Act: -0.1700
Data Index: 125857 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.2697. Min Act: -0.1700
Data Index: 4971181 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1135. Min Range: -6.1135
Max Act: 5.2385. Min Act: -0.1700
Data Index: 3016478 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19