Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6063 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0143. Min Range: -9.0143
Max Act: 9.0143. Min Act: -0.1700
Data Index: 5039073 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.8268. Min Act: -0.1700
Data Index: 722081 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.7643. Min Act: -0.1700
Data Index: 4001535 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.7643. Min Act: -0.1700
Data Index: 8670689 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.7018. Min Act: -0.1700
Data Index: 4646436 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.7018. Min Act: -0.1700
Data Index: 7633012 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.6393. Min Act: -0.1700
Data Index: 4779647 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.6393. Min Act: -0.1700
Data Index: 1045417 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.5768. Min Act: -0.1700
Data Index: 3090951 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.5143. Min Act: -0.1700
Data Index: 704853 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.3893. Min Act: -0.1700
Data Index: 8627883 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.3893. Min Act: -0.1700
Data Index: 3157840 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.3893. Min Act: -0.1700
Data Index: 4590412 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.3268. Min Act: -0.1700
Data Index: 3198440 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.2643. Min Act: -0.1700
Data Index: 2537980 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.3268. Min Act: -0.1700
Data Index: 6669567 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.2018. Min Act: -0.1700
Data Index: 6202504 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.2643. Min Act: -0.1700
Data Index: 2076743 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.2018. Min Act: -0.1700
Data Index: 195729 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0143. Min Range: -9.0143
Max Act: 8.2018. Min Act: -0.1700
Data Index: 6758458 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19