Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 737 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1222. Min Range: -9.1222
Max Act: 9.1222. Min Act: -0.1700
Data Index: 1836537 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.5597. Min Act: -0.1700
Data Index: 1630631 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.4972. Min Act: -0.1700
Data Index: 4332453 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.4972. Min Act: -0.1700
Data Index: 8002124 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.4972. Min Act: -0.1700
Data Index: 660253 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.4972. Min Act: -0.1700
Data Index: 7309990 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.4347. Min Act: -0.1700
Data Index: 3875236 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.4347. Min Act: -0.1700
Data Index: 1854483 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.4972. Min Act: -0.1700
Data Index: 7334260 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.4347. Min Act: -0.1700
Data Index: 6520864 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.4347. Min Act: -0.1700
Data Index: 6288413 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.3722. Min Act: -0.1700
Data Index: 6439899 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.3722. Min Act: -0.1700
Data Index: 2562673 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.3097. Min Act: -0.1700
Data Index: 926737 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.3097. Min Act: -0.1700
Data Index: 4507667 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.3097. Min Act: -0.1700
Data Index: 764008 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.3097. Min Act: -0.1700
Data Index: 7335511 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.3097. Min Act: -0.1700
Data Index: 8083896 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.2472. Min Act: -0.1700
Data Index: 3007892 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1222. Min Range: -9.1222
Max Act: 8.2472. Min Act: -0.1700
Data Index: 2584188 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19