Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3158 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.1823. Min Range: -10.1823
Max Act: 10.1823. Min Act: -0.1700
Data Index: 2915005 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.9948. Min Act: -0.1700
Data Index: 3790932 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.7448. Min Act: -0.1698
Data Index: 7300635 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.8073. Min Act: -0.1700
Data Index: 2087124 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.6823. Min Act: -0.1700
Data Index: 6815238 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.6823. Min Act: -0.1700
Data Index: 3061672 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.6823. Min Act: -0.1700
Data Index: 700510 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.6823. Min Act: -0.1700
Data Index: 7691421 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.6823. Min Act: -0.1700
Data Index: 5223877 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.6823. Min Act: -0.1699
Data Index: 7594746 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.6198. Min Act: -0.1700
Data Index: 2756690 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.6198. Min Act: -0.1698
Data Index: 4895792 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.6198. Min Act: -0.1700
Data Index: 4096549 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.6198. Min Act: -0.1700
Data Index: 930071 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.5573. Min Act: -0.1700
Data Index: 3971234 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.6198. Min Act: -0.1700
Data Index: 3795982 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.5573. Min Act: -0.1700
Data Index: 3660132 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.4948. Min Act: -0.1700
Data Index: 338067 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.4948. Min Act: -0.1700
Data Index: 6794792 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1823. Min Range: -10.1823
Max Act: 9.4948. Min Act: -0.1700
Data Index: 3043748 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19