Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.5630. Min Act: -0.1700
Data Index: 4005586 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.4692. Min Act: -0.1700
Data Index: 6105248 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.4380. Min Act: -0.1700
Data Index: 792710 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.4067. Min Act: -0.1700
Data Index: 4927580 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.3755. Min Act: -0.1700
Data Index: 2642210 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.3442. Min Act: -0.1700
Data Index: 8513463 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.3442. Min Act: -0.1700
Data Index: 8034440 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.3130. Min Act: -0.1700
Data Index: 3011382 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.2817. Min Act: -0.1700
Data Index: 5483463 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.3130. Min Act: -0.1700
Data Index: 1136876 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.2817. Min Act: -0.1700
Data Index: 454288 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.2817. Min Act: -0.1700
Data Index: 2868257 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.2505. Min Act: -0.1700
Data Index: 6482048 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.2817. Min Act: -0.1700
Data Index: 4049215 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.2192. Min Act: -0.1700
Data Index: 322738 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.2505. Min Act: -0.1700
Data Index: 5859781 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.2192. Min Act: -0.1700
Data Index: 306181 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.1567. Min Act: -0.1700
Data Index: 1990306 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.1567. Min Act: -0.1700
Data Index: 1406977 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.1567. Min Act: -0.1700
Data Index: 7378792 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19