Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2910 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 24.2158. Min Range: -24.2158
Max Act: 24.2158. Min Act: -0.1700
Data Index: 3441131 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.8408. Min Act: -0.1696
Data Index: 4231051 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.8408. Min Act: -0.1685
Data Index: 300830 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.8408. Min Act: -0.1699
Data Index: 5374790 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.8408. Min Act: -0.1696
Data Index: 4586293 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.5908. Min Act: -0.1700
Data Index: 2302928 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.7158. Min Act: -0.1690
Data Index: 1047874 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.7158. Min Act: -0.1700
Data Index: 2712717 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.7158. Min Act: -0.1687
Data Index: 6295868 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.7158. Min Act: -0.1700
Data Index: 6526073 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.7158. Min Act: -0.1700
Data Index: 2801629 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.7158. Min Act: -0.1698
Data Index: 4135011 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.7158. Min Act: -0.1697
Data Index: 7017842 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.7158. Min Act: -0.1697
Data Index: 130370 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.7158. Min Act: -0.1700
Data Index: 8084585 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.7158. Min Act: -0.1700
Data Index: 651078 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.7158. Min Act: -0.1689
Data Index: 4028282 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.5908. Min Act: -0.1700
Data Index: 3761114 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.5908. Min Act: -0.1699
Data Index: 3863884 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 24.2158. Min Range: -24.2158
Max Act: 23.5908. Min Act: -0.1700
Data Index: 3945825 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19