Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.1989. Min Act: -0.1700
Data Index: 7796918 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.1677. Min Act: -0.1700
Data Index: 2728524 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.1677. Min Act: -0.1700
Data Index: 4215705 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.1364. Min Act: -0.1700
Data Index: 1405546 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.1364. Min Act: -0.1700
Data Index: 1716595 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.1364. Min Act: -0.1700
Data Index: 25770 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.1052. Min Act: -0.1700
Data Index: 417077 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.1052. Min Act: -0.1700
Data Index: 7234023 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.1052. Min Act: -0.1700
Data Index: 1682508 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.1052. Min Act: -0.1700
Data Index: 8772575 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.1052. Min Act: -0.1700
Data Index: 2839684 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.0427. Min Act: -0.1700
Data Index: 4984670 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.0427. Min Act: -0.1700
Data Index: 8029607 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.0739. Min Act: -0.1700
Data Index: 956522 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.0739. Min Act: -0.1700
Data Index: 1596809 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.0739. Min Act: -0.1700
Data Index: 700766 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.0427. Min Act: -0.1700
Data Index: 7836663 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.0427. Min Act: -0.1700
Data Index: 894579 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.0114. Min Act: -0.1700
Data Index: 3193398 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1989. Min Range: -7.1989
Max Act: 7.0427. Min Act: -0.1700
Data Index: 3018609 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19