Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5850 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.8497. Min Act: 0.0501
Data Index: 4971766 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.8326. Min Act: 0.0315
Data Index: 7643249 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.8154. Min Act: -0.0886
Data Index: 6050388 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7896. Min Act: -0.1262
Data Index: 2312297 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.8068. Min Act: -0.0588
Data Index: 7249024 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.8068. Min Act: 0.1267
Data Index: 3161511 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.8068. Min Act: 0.1280
Data Index: 8513473 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7810. Min Act: -0.0886
Data Index: 6050385 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7724. Min Act: -0.0477
Data Index: 4325384 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7637. Min Act: 0.0815
Data Index: 5727175 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7637. Min Act: -0.0937
Data Index: 424478 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7724. Min Act: 0.1426
Data Index: 5567533 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7551. Min Act: -0.1356
Data Index: 5611642 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7551. Min Act: -0.0619
Data Index: 5859955 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7378. Min Act: 0.1074
Data Index: 8305862 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7465. Min Act: -0.1175
Data Index: 4276747 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7465. Min Act: -0.0751
Data Index: 3520331 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7465. Min Act: 0.0615
Data Index: 5679041 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7378. Min Act: 0.0067
Data Index: 6788491 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8497. Min Range: -1.8497
Max Act: 1.7378. Min Act: -0.1225
Data Index: 2817272 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19