Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1692 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.3774. Min Act: -0.1700
Data Index: 6304101 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.4087. Min Act: -0.1700
Data Index: 6762256 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.2524. Min Act: -0.1700
Data Index: 2415401 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.2212. Min Act: -0.1700
Data Index: 6497643 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.2212. Min Act: -0.1700
Data Index: 1590479 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.1899. Min Act: -0.1700
Data Index: 5687432 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.1899. Min Act: -0.1700
Data Index: 2129177 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.1899. Min Act: -0.1700
Data Index: 2018451 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.1586. Min Act: -0.1700
Data Index: 6959309 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.1899. Min Act: -0.1700
Data Index: 5196283 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.1586. Min Act: -0.1700
Data Index: 2643087 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.1274. Min Act: -0.1700
Data Index: 5764376 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.1274. Min Act: -0.1700
Data Index: 1246653 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.1274. Min Act: -0.1700
Data Index: 3546575 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.0961. Min Act: -0.1700
Data Index: 3806858 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.1274. Min Act: -0.1700
Data Index: 6308277 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.1274. Min Act: -0.1700
Data Index: 5276283 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.0961. Min Act: -0.1700
Data Index: 2266886 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.0961. Min Act: -0.1700
Data Index: 110917 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4087. Min Range: -4.4087
Max Act: 4.0961. Min Act: -0.1700
Data Index: 4817260 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19