Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 331 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0237. Min Range: -7.0237
Max Act: 7.0237. Min Act: -0.1700
Data Index: 477751 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.9924. Min Act: -0.1700
Data Index: 6783385 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.9299. Min Act: -0.1700
Data Index: 8326684 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.8362. Min Act: -0.1700
Data Index: 5171581 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.8049. Min Act: -0.1700
Data Index: 5100783 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.7737. Min Act: -0.1700
Data Index: 8129179 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.7424. Min Act: -0.1700
Data Index: 7991467 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.7424. Min Act: -0.1700
Data Index: 3336399 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.7112. Min Act: -0.1700
Data Index: 4874236 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.7112. Min Act: -0.1700
Data Index: 449874 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.7112. Min Act: -0.1700
Data Index: 2331243 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.6487. Min Act: -0.1700
Data Index: 2278471 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.7112. Min Act: -0.1700
Data Index: 1698266 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.6799. Min Act: -0.1700
Data Index: 5267892 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.6487. Min Act: -0.1700
Data Index: 597645 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.6174. Min Act: -0.1700
Data Index: 6555206 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.5549. Min Act: -0.1700
Data Index: 3314224 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.5862. Min Act: -0.1700
Data Index: 4895229 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.5549. Min Act: -0.1700
Data Index: 1534013 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0237. Min Range: -7.0237
Max Act: 6.5862. Min Act: -0.1700
Data Index: 2436481 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19