Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.3642. Min Act: -0.1700
Data Index: 4849296 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.3015. Min Act: -0.1700
Data Index: 4199617 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.2858. Min Act: -0.1700
Data Index: 37518 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.2229. Min Act: -0.1700
Data Index: 182546 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.2072. Min Act: -0.1700
Data Index: 6506282 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.1758. Min Act: -0.1700
Data Index: 3790544 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.1600. Min Act: -0.1700
Data Index: 2450343 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.1443. Min Act: -0.1700
Data Index: 3794138 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.1443. Min Act: -0.1700
Data Index: 4462499 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.1600. Min Act: -0.1700
Data Index: 8370143 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.1285. Min Act: -0.1700
Data Index: 4912033 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.1285. Min Act: -0.1700
Data Index: 1925012 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.1128. Min Act: -0.1700
Data Index: 7919554 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.0970. Min Act: -0.1700
Data Index: 7815045 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.0970. Min Act: -0.1700
Data Index: 1248013 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.0813. Min Act: -0.1700
Data Index: 407317 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.0813. Min Act: -0.1700
Data Index: 5818953 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.0813. Min Act: -0.1700
Data Index: 1027862 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.0813. Min Act: -0.1700
Data Index: 4912037 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3642. Min Range: -3.3642
Max Act: 3.0655. Min Act: -0.1700
Data Index: 5367052 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19