Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3730 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.8892. Min Act: -0.1700
Data Index: 6686444 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.8382. Min Act: -0.1696
Data Index: 4460792 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.8129. Min Act: -0.1689
Data Index: 1673301 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.8045. Min Act: -0.1700
Data Index: 4460790 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.8045. Min Act: -0.1698
Data Index: 6434927 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.7878. Min Act: -0.1700
Data Index: 7166540 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.7711. Min Act: -0.1657
Data Index: 2024589 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.7711. Min Act: -0.1697
Data Index: 5954349 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.7628. Min Act: -0.1699
Data Index: 4861876 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.7545. Min Act: -0.1696
Data Index: 2640647 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.7379. Min Act: -0.1699
Data Index: 7354055 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.6969. Min Act: -0.1700
Data Index: 5794990 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.7133. Min Act: -0.1700
Data Index: 195783 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.7051. Min Act: -0.1696
Data Index: 7446393 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.6969. Min Act: -0.1700
Data Index: 3923456 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.6888. Min Act: -0.1700
Data Index: 4428490 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.6888. Min Act: -0.1696
Data Index: 4362731 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.6888. Min Act: -0.1696
Data Index: 425734 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.6969. Min Act: -0.1700
Data Index: 7385577 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8892. Min Range: -0.8892
Max Act: 0.6969. Min Act: -0.1700
Data Index: 2008231 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19