Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2949 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.7075. Min Act: -0.1700
Data Index: 2859780 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.6450. Min Act: -0.1700
Data Index: 5511587 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.5825. Min Act: -0.1700
Data Index: 5327001 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.5825. Min Act: -0.1700
Data Index: 389210 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.4575. Min Act: -0.1700
Data Index: 5305971 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.2700. Min Act: -0.1700
Data Index: 5936902 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.2700. Min Act: -0.1700
Data Index: 745763 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.2700. Min Act: -0.1700
Data Index: 3976241 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.2075. Min Act: -0.1700
Data Index: 5324315 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.2075. Min Act: -0.1700
Data Index: 968108 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.2388. Min Act: -0.1700
Data Index: 6923747 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.1763. Min Act: -0.1700
Data Index: 3110602 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.1450. Min Act: -0.1700
Data Index: 3401452 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.1450. Min Act: -0.1700
Data Index: 3426444 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.1450. Min Act: -0.1700
Data Index: 5511584 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.0200. Min Act: -0.1700
Data Index: 5971252 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.0513. Min Act: -0.1700
Data Index: 6809641 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.0200. Min Act: -0.1700
Data Index: 3156366 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.0513. Min Act: -0.1700
Data Index: 745762 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7075. Min Range: -8.7075
Max Act: 8.0513. Min Act: -0.1700
Data Index: 391558 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19