Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3860 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1214. Min Range: -2.1214
Max Act: 2.1214. Min Act: -0.1700
Data Index: 6819532 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1214. Min Range: -2.1214
Max Act: 2.0206. Min Act: -0.1700
Data Index: 361179 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9699. Min Act: -0.1700
Data Index: 1201439 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9699. Min Act: -0.1700
Data Index: 1180555 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9614. Min Act: -0.1700
Data Index: 4453637 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9699. Min Act: -0.1700
Data Index: 7850154 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9699. Min Act: -0.1700
Data Index: 6006630 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9530. Min Act: -0.1700
Data Index: 50336 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9530. Min Act: -0.1700
Data Index: 1842729 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9190. Min Act: -0.1700
Data Index: 4856667 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9445. Min Act: -0.1700
Data Index: 3083900 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9360. Min Act: -0.1700
Data Index: 3446483 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9019. Min Act: -0.1700
Data Index: 5078783 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9190. Min Act: -0.1700
Data Index: 3618186 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9190. Min Act: -0.1700
Data Index: 2183910 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9190. Min Act: -0.1700
Data Index: 7001353 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9104. Min Act: -0.1700
Data Index: 1882791 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9190. Min Act: -0.1700
Data Index: 605497 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9190. Min Act: -0.1700
Data Index: 4496496 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1214. Min Range: -2.1214
Max Act: 1.9019. Min Act: -0.1700
Data Index: 15784 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19