Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5143 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.3517. Min Act: -0.1700
Data Index: 4212978 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.2418. Min Act: -0.1700
Data Index: 6945514 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.2261. Min Act: -0.1700
Data Index: 668174 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.2104. Min Act: -0.1700
Data Index: 4761810 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1946. Min Act: -0.1700
Data Index: 928619 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1789. Min Act: -0.1700
Data Index: 2899238 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1789. Min Act: -0.1700
Data Index: 3323902 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1789. Min Act: -0.1700
Data Index: 1152591 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1789. Min Act: -0.1700
Data Index: 3321221 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1317. Min Act: -0.1700
Data Index: 2375008 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1474. Min Act: -0.1700
Data Index: 6352071 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1317. Min Act: -0.1700
Data Index: 7544105 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1159. Min Act: -0.1700
Data Index: 6046811 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1317. Min Act: -0.1700
Data Index: 653392 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1317. Min Act: -0.1700
Data Index: 1092283 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1159. Min Act: -0.1700
Data Index: 381266 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1159. Min Act: -0.1700
Data Index: 3666349 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1159. Min Act: -0.1700
Data Index: 2600938 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.1002. Min Act: -0.1700
Data Index: 6802212 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3517. Min Range: -3.3517
Max Act: 3.0844. Min Act: -0.1700
Data Index: 3873212 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19