Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2089 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4082. Min Range: -8.4082
Max Act: 8.4082. Min Act: -0.1700
Data Index: 650537 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4082. Min Range: -8.4082
Max Act: 8.2832. Min Act: -0.1700
Data Index: 6615596 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4082. Min Range: -8.4082
Max Act: 8.2207. Min Act: -0.1700
Data Index: 511741 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4082. Min Range: -8.4082
Max Act: 8.1582. Min Act: -0.1700
Data Index: 8274628 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4082. Min Range: -8.4082
Max Act: 8.1582. Min Act: -0.1700
Data Index: 6624223 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4082. Min Range: -8.4082
Max Act: 8.1582. Min Act: -0.1700
Data Index: 6715115 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4082. Min Range: -8.4082
Max Act: 8.0332. Min Act: -0.1700
Data Index: 1961515 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4082. Min Range: -8.4082
Max Act: 7.9707. Min Act: -0.1700
Data Index: 6199647 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4082. Min Range: -8.4082
Max Act: 7.9707. Min Act: -0.1700
Data Index: 4138426 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4082. Min Range: -8.4082
Max Act: 7.9707. Min Act: -0.1700
Data Index: 6272123 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4082. Min Range: -8.4082
Max Act: 7.9082. Min Act: -0.1700
Data Index: 8448050 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4082. Min Range: -8.4082
Max Act: 7.9082. Min Act: -0.1700
Data Index: 247999 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4082. Min Range: -8.4082
Max Act: 7.9082. Min Act: -0.1700
Data Index: 928136 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4082. Min Range: -8.4082
Max Act: 7.9082. Min Act: -0.1700
Data Index: 7742878 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4082. Min Range: -8.4082
Max Act: 7.8457. Min Act: -0.1700
Data Index: 3361495 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4082. Min Range: -8.4082
Max Act: 7.8457. Min Act: -0.1700
Data Index: 7488000 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4082. Min Range: -8.4082
Max Act: 7.8457. Min Act: -0.1700
Data Index: 3327223 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4082. Min Range: -8.4082
Max Act: 7.7832. Min Act: -0.1700
Data Index: 2011432 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4082. Min Range: -8.4082
Max Act: 7.7832. Min Act: -0.1700
Data Index: 6720327 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4082. Min Range: -8.4082
Max Act: 7.7832. Min Act: -0.1700
Data Index: 1531645 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19