Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1855 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.5768. Min Act: -0.1700
Data Index: 4424497 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.5455. Min Act: -0.1700
Data Index: 6375131 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.4515. Min Act: -0.1700
Data Index: 4951862 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.4515. Min Act: -0.1700
Data Index: 4974636 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.4358. Min Act: -0.1700
Data Index: 7201767 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.4201. Min Act: -0.1700
Data Index: 1051831 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.4045. Min Act: -0.1700
Data Index: 5323867 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.4045. Min Act: -0.1700
Data Index: 4473518 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.4045. Min Act: -0.1700
Data Index: 623987 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.3731. Min Act: -0.1700
Data Index: 8205197 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.3417. Min Act: -0.1700
Data Index: 7165928 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.3731. Min Act: -0.1700
Data Index: 458597 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.3574. Min Act: -0.1700
Data Index: 5015919 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.3574. Min Act: -0.1700
Data Index: 2604344 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.3574. Min Act: -0.1700
Data Index: 3247150 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.3104. Min Act: -0.1700
Data Index: 5553188 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.3417. Min Act: -0.1700
Data Index: 4487519 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.3260. Min Act: -0.1700
Data Index: 5720141 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.3104. Min Act: -0.1700
Data Index: 158719 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5768. Min Range: -3.5768
Max Act: 3.3260. Min Act: -0.1700
Data Index: 299613 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19