Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1155 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.4823. Min Act: -0.1698
Data Index: 5831123 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.4295. Min Act: -0.1689
Data Index: 1631870 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.4207. Min Act: -0.1700
Data Index: 102737 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.4031. Min Act: -0.1700
Data Index: 6267213 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.4119. Min Act: -0.1699
Data Index: 3044643 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3943. Min Act: -0.1700
Data Index: 7253854 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3766. Min Act: -0.1699
Data Index: 7306532 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3678. Min Act: -0.1700
Data Index: 645865 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3678. Min Act: -0.1700
Data Index: 8046797 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3678. Min Act: -0.1695
Data Index: 4602266 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3766. Min Act: -0.1700
Data Index: 6378759 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3590. Min Act: -0.1700
Data Index: 3750378 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3502. Min Act: -0.1699
Data Index: 5902741 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3502. Min Act: -0.1700
Data Index: 5901648 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3502. Min Act: -0.1688
Data Index: 4832071 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3502. Min Act: -0.1699
Data Index: 167300 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3502. Min Act: -0.1700
Data Index: 5118786 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3414. Min Act: -0.1695
Data Index: 7516515 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3414. Min Act: -0.1699
Data Index: 3611443 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4823. Min Range: -1.4823
Max Act: 1.3326. Min Act: -0.1700
Data Index: 2340455 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19