Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7038. Min Range: -8.7038
Max Act: 8.7038. Min Act: -0.1700
Data Index: 140342 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7038. Min Range: -8.7038
Max Act: 8.6413. Min Act: -0.1700
Data Index: 8493336 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7038. Min Range: -8.7038
Max Act: 8.6413. Min Act: -0.1700
Data Index: 4971810 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7038. Min Range: -8.7038
Max Act: 8.4538. Min Act: -0.1700
Data Index: 4971813 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7038. Min Range: -8.7038
Max Act: 8.4538. Min Act: -0.1700
Data Index: 6918075 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7038. Min Range: -8.7038
Max Act: 8.3913. Min Act: -0.1700
Data Index: 5692526 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7038. Min Range: -8.7038
Max Act: 8.2663. Min Act: -0.1700
Data Index: 8473414 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7038. Min Range: -8.7038
Max Act: 8.2663. Min Act: -0.1700
Data Index: 3456385 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7038. Min Range: -8.7038
Max Act: 8.2663. Min Act: -0.1700
Data Index: 4072902 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7038. Min Range: -8.7038
Max Act: 7.9538. Min Act: -0.1700
Data Index: 175430 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7038. Min Range: -8.7038
Max Act: 7.9538. Min Act: -0.1700
Data Index: 7754663 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7038. Min Range: -8.7038
Max Act: 7.8913. Min Act: -0.1700
Data Index: 140338 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7038. Min Range: -8.7038
Max Act: 7.8288. Min Act: -0.1700
Data Index: 1381774 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7038. Min Range: -8.7038
Max Act: 7.8288. Min Act: -0.1700
Data Index: 2688686 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7038. Min Range: -8.7038
Max Act: 7.8288. Min Act: -0.1700
Data Index: 4971812 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7038. Min Range: -8.7038
Max Act: 7.7975. Min Act: -0.1700
Data Index: 509335 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7038. Min Range: -8.7038
Max Act: 7.7975. Min Act: -0.1700
Data Index: 8716471 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7038. Min Range: -8.7038
Max Act: 7.7663. Min Act: -0.1700
Data Index: 5920482 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7038. Min Range: -8.7038
Max Act: 7.7350. Min Act: -0.1700
Data Index: 348122 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7038. Min Range: -8.7038
Max Act: 7.7350. Min Act: -0.1700
Data Index: 5752594 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19