Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3014 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4180. Min Range: -5.4180
Max Act: 5.4180. Min Act: -0.1700
Data Index: 729123 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4180. Min Range: -5.4180
Max Act: 5.3868. Min Act: -0.1700
Data Index: 2541672 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4180. Min Range: -5.4180
Max Act: 5.2930. Min Act: -0.1700
Data Index: 2355517 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4180. Min Range: -5.4180
Max Act: 5.2618. Min Act: -0.1699
Data Index: 177601 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4180. Min Range: -5.4180
Max Act: 5.1680. Min Act: -0.1700
Data Index: 4215418 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4180. Min Range: -5.4180
Max Act: 5.1680. Min Act: -0.1700
Data Index: 3463121 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4180. Min Range: -5.4180
Max Act: 5.1368. Min Act: -0.1700
Data Index: 7088631 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4180. Min Range: -5.4180
Max Act: 5.1055. Min Act: -0.1700
Data Index: 2313402 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4180. Min Range: -5.4180
Max Act: 5.1055. Min Act: -0.1700
Data Index: 4184641 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4180. Min Range: -5.4180
Max Act: 5.0430. Min Act: -0.1700
Data Index: 429592 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4180. Min Range: -5.4180
Max Act: 5.0430. Min Act: -0.1700
Data Index: 6040683 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4180. Min Range: -5.4180
Max Act: 5.0118. Min Act: -0.1700
Data Index: 7303854 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4180. Min Range: -5.4180
Max Act: 4.9805. Min Act: -0.1700
Data Index: 908627 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4180. Min Range: -5.4180
Max Act: 4.9493. Min Act: -0.1700
Data Index: 2203338 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4180. Min Range: -5.4180
Max Act: 4.9493. Min Act: -0.1700
Data Index: 6851709 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4180. Min Range: -5.4180
Max Act: 4.9805. Min Act: -0.1700
Data Index: 2706671 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4180. Min Range: -5.4180
Max Act: 4.9805. Min Act: -0.1700
Data Index: 2181280 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4180. Min Range: -5.4180
Max Act: 4.9805. Min Act: -0.1700
Data Index: 8499699 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4180. Min Range: -5.4180
Max Act: 4.9493. Min Act: -0.1700
Data Index: 3366007 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4180. Min Range: -5.4180
Max Act: 4.9493. Min Act: -0.1700
Data Index: 5085134 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19