Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4641 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2484. Min Range: -7.2484
Max Act: 7.2484. Min Act: -0.1700
Data Index: 5532760 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.8421. Min Act: -0.1700
Data Index: 5491644 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.7171. Min Act: -0.1700
Data Index: 3524452 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.6546. Min Act: -0.1700
Data Index: 4956170 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.6546. Min Act: -0.1700
Data Index: 4358527 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.4671. Min Act: -0.1700
Data Index: 2062512 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.4671. Min Act: -0.1700
Data Index: 4337695 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.4046. Min Act: -0.1700
Data Index: 4113645 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.4046. Min Act: -0.1700
Data Index: 2109486 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.4046. Min Act: -0.1700
Data Index: 2998783 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.3734. Min Act: -0.1700
Data Index: 5221645 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.3734. Min Act: -0.1700
Data Index: 7628046 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.3421. Min Act: -0.1700
Data Index: 34638 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.3109. Min Act: -0.1700
Data Index: 5791249 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.3109. Min Act: -0.1700
Data Index: 7450065 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.2796. Min Act: -0.1700
Data Index: 806098 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.2484. Min Act: -0.1700
Data Index: 7526371 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.2171. Min Act: -0.1700
Data Index: 7372986 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.2171. Min Act: -0.1700
Data Index: 3969840 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2484. Min Range: -7.2484
Max Act: 6.1859. Min Act: -0.1700
Data Index: 6999737 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19