Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3651 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7560. Min Range: -7.7560
Max Act: 7.7560. Min Act: -0.1700
Data Index: 913021 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7560. Min Range: -7.7560
Max Act: 7.0372. Min Act: -0.1700
Data Index: 7088431 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.7872. Min Act: -0.1700
Data Index: 440672 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.7872. Min Act: -0.1700
Data Index: 6999059 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.7872. Min Act: -0.1700
Data Index: 7020910 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.7247. Min Act: -0.1700
Data Index: 3894691 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.7247. Min Act: -0.1700
Data Index: 3066639 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.7247. Min Act: -0.1700
Data Index: 4704502 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.6622. Min Act: -0.1700
Data Index: 4563428 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.6310. Min Act: -0.1700
Data Index: 8029441 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.6622. Min Act: -0.1700
Data Index: 8485270 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.6622. Min Act: -0.1700
Data Index: 221000 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.6310. Min Act: -0.1700
Data Index: 7625076 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.6310. Min Act: -0.1700
Data Index: 6285999 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.6310. Min Act: -0.1700
Data Index: 315978 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.5997. Min Act: -0.1700
Data Index: 2711331 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.5685. Min Act: -0.1700
Data Index: 2666002 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.5685. Min Act: -0.1700
Data Index: 4397515 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.5685. Min Act: -0.1700
Data Index: 2183803 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7560. Min Range: -7.7560
Max Act: 6.5685. Min Act: -0.1700
Data Index: 3429155 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19