Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1198 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.7808. Min Act: -0.1700
Data Index: 3377580 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.7489. Min Act: -0.1700
Data Index: 2853722 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.7489. Min Act: -0.1700
Data Index: 2871070 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.7489. Min Act: -0.1700
Data Index: 5475269 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.7489. Min Act: -0.1700
Data Index: 2838865 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.7489. Min Act: -0.1700
Data Index: 6827591 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.7170. Min Act: -0.1700
Data Index: 1251730 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.7170. Min Act: -0.1700
Data Index: 6827592 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.6850. Min Act: -0.1700
Data Index: 5155699 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.6850. Min Act: -0.1700
Data Index: 2871055 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.6850. Min Act: -0.1700
Data Index: 3398079 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.6689. Min Act: -0.1700
Data Index: 6884371 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.6850. Min Act: -0.1700
Data Index: 2871062 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.6368. Min Act: -0.1700
Data Index: 764612 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.6368. Min Act: -0.1700
Data Index: 555456 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.6368. Min Act: -0.1700
Data Index: 718702 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.6368. Min Act: -0.1700
Data Index: 4757128 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.6208. Min Act: -0.1700
Data Index: 7469073 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.6368. Min Act: -0.1700
Data Index: 4246532 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7808. Min Range: -2.7808
Max Act: 2.6208. Min Act: -0.1700
Data Index: 1608788 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19