Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.8048. Min Range: -12.8048
Max Act: 12.8048. Min Act: -0.1700
Data Index: 7265133 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8048. Min Range: -12.8048
Max Act: 12.2423. Min Act: -0.1700
Data Index: 2226647 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.8673. Min Act: -0.1700
Data Index: 2535112 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.7423. Min Act: -0.1700
Data Index: 3385233 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.6173. Min Act: -0.1700
Data Index: 4445297 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.6173. Min Act: -0.1700
Data Index: 3612491 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.4298. Min Act: -0.1700
Data Index: 2446225 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.4923. Min Act: -0.1700
Data Index: 5057658 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.4298. Min Act: -0.1700
Data Index: 763729 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.4923. Min Act: -0.1700
Data Index: 5110008 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.4298. Min Act: -0.1700
Data Index: 4669592 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.4298. Min Act: -0.1700
Data Index: 5505484 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.4298. Min Act: -0.1700
Data Index: 2368824 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.4298. Min Act: -0.1700
Data Index: 5859209 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.4298. Min Act: -0.1700
Data Index: 471574 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.3673. Min Act: -0.1700
Data Index: 466403 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.4298. Min Act: -0.1700
Data Index: 7330524 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.3673. Min Act: -0.1700
Data Index: 535511 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.3673. Min Act: -0.1700
Data Index: 71088 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8048. Min Range: -12.8048
Max Act: 11.3673. Min Act: -0.1700
Data Index: 1818281 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19