Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3152 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.9784. Min Act: -0.1700
Data Index: 4453751 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.9159. Min Act: -0.1700
Data Index: 5264280 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.7909. Min Act: -0.1700
Data Index: 1549699 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.7597. Min Act: -0.1700
Data Index: 1152646 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.7284. Min Act: -0.1700
Data Index: 8772516 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.6659. Min Act: -0.1700
Data Index: 2574423 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.6034. Min Act: -0.1700
Data Index: 4007166 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.6347. Min Act: -0.1700
Data Index: 3432604 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.6347. Min Act: -0.1700
Data Index: 1137886 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.6034. Min Act: -0.1700
Data Index: 8706069 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.6034. Min Act: -0.1700
Data Index: 432592 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.6034. Min Act: -0.1700
Data Index: 7900872 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.5722. Min Act: -0.1700
Data Index: 3015204 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.5722. Min Act: -0.1700
Data Index: 3468178 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.5722. Min Act: -0.1700
Data Index: 4732343 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.5722. Min Act: -0.1700
Data Index: 6665366 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.5409. Min Act: -0.1700
Data Index: 2489538 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.5722. Min Act: -0.1700
Data Index: 2338681 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.5409. Min Act: -0.1700
Data Index: 7576699 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9784. Min Range: -5.9784
Max Act: 5.5409. Min Act: -0.1700
Data Index: 7259339 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19