Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2159 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0532. Min Range: -6.0532
Max Act: 6.0532. Min Act: -0.1700
Data Index: 6159307 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0532. Min Range: -6.0532
Max Act: 6.0532. Min Act: -0.1700
Data Index: 3307115 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.9907. Min Act: -0.1700
Data Index: 4071093 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.9594. Min Act: -0.1700
Data Index: 7321004 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.9282. Min Act: -0.1700
Data Index: 805812 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.9282. Min Act: -0.1700
Data Index: 3956970 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.8969. Min Act: -0.1700
Data Index: 7367840 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.8969. Min Act: -0.1700
Data Index: 1501590 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.8657. Min Act: -0.1700
Data Index: 146048 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.8657. Min Act: -0.1700
Data Index: 6758683 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.8032. Min Act: -0.1700
Data Index: 7242341 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.8344. Min Act: -0.1700
Data Index: 7790713 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.7719. Min Act: -0.1700
Data Index: 7897336 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.7407. Min Act: -0.1700
Data Index: 1108924 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.7094. Min Act: -0.1700
Data Index: 2161866 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.7407. Min Act: -0.1700
Data Index: 7748395 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.7094. Min Act: -0.1700
Data Index: 3572531 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.6782. Min Act: -0.1700
Data Index: 8230320 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.6469. Min Act: -0.1700
Data Index: 5066501 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0532. Min Range: -6.0532
Max Act: 5.6782. Min Act: -0.1700
Data Index: 3429329 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19