Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3900 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0878. Min Range: -2.0878
Max Act: 2.0878. Min Act: -0.1700
Data Index: 937937 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0878. Min Range: -2.0878
Max Act: 2.0542. Min Act: -0.1700
Data Index: 7277924 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0878. Min Range: -2.0878
Max Act: 2.0374. Min Act: -0.1700
Data Index: 7769647 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0878. Min Range: -2.0878
Max Act: 2.0374. Min Act: -0.1700
Data Index: 6098144 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0878. Min Range: -2.0878
Max Act: 2.0205. Min Act: -0.1700
Data Index: 1681722 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0878. Min Range: -2.0878
Max Act: 2.0205. Min Act: -0.1700
Data Index: 1955194 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0878. Min Range: -2.0878
Max Act: 2.0205. Min Act: -0.1699
Data Index: 4657048 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0878. Min Range: -2.0878
Max Act: 2.0205. Min Act: -0.1700
Data Index: 1913482 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0878. Min Range: -2.0878
Max Act: 2.0036. Min Act: -0.1700
Data Index: 5749975 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0878. Min Range: -2.0878
Max Act: 2.0036. Min Act: -0.1700
Data Index: 99224 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0878. Min Range: -2.0878
Max Act: 1.9867. Min Act: -0.1700
Data Index: 8460748 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0878. Min Range: -2.0878
Max Act: 1.9867. Min Act: -0.1700
Data Index: 1179883 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0878. Min Range: -2.0878
Max Act: 1.9698. Min Act: -0.1700
Data Index: 3669539 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0878. Min Range: -2.0878
Max Act: 1.9867. Min Act: -0.1700
Data Index: 4608352 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0878. Min Range: -2.0878
Max Act: 1.9698. Min Act: -0.1700
Data Index: 378886 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0878. Min Range: -2.0878
Max Act: 1.9698. Min Act: -0.1700
Data Index: 753425 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0878. Min Range: -2.0878
Max Act: 1.9698. Min Act: -0.1700
Data Index: 1557932 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0878. Min Range: -2.0878
Max Act: 1.9528. Min Act: -0.1700
Data Index: 3533603 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0878. Min Range: -2.0878
Max Act: 1.9867. Min Act: -0.1700
Data Index: 1670093 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0878. Min Range: -2.0878
Max Act: 1.9698. Min Act: -0.1700
Data Index: 7559417 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19