Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2630. Min Range: -6.2630
Max Act: 6.2630. Min Act: -0.1700
Data Index: 488510 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2630. Min Range: -6.2630
Max Act: 6.2630. Min Act: -0.1700
Data Index: 3881449 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2630. Min Range: -6.2630
Max Act: 6.2318. Min Act: -0.1700
Data Index: 4133274 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2630. Min Range: -6.2630
Max Act: 6.1068. Min Act: -0.1700
Data Index: 8500029 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2630. Min Range: -6.2630
Max Act: 6.0443. Min Act: -0.1700
Data Index: 6939692 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.9505. Min Act: -0.1700
Data Index: 689023 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.8880. Min Act: -0.1700
Data Index: 8490666 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.8880. Min Act: -0.1700
Data Index: 6420445 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.8568. Min Act: -0.1700
Data Index: 6674664 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.8568. Min Act: -0.1700
Data Index: 7478495 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.8255. Min Act: -0.1700
Data Index: 3163564 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.8255. Min Act: -0.1700
Data Index: 1994160 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.7630. Min Act: -0.1700
Data Index: 1347907 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.7630. Min Act: -0.1700
Data Index: 2321335 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.7630. Min Act: -0.1700
Data Index: 4808601 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.7318. Min Act: -0.1700
Data Index: 5047877 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.7318. Min Act: -0.1700
Data Index: 2479151 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.7318. Min Act: -0.1700
Data Index: 4202405 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.7318. Min Act: -0.1700
Data Index: 5689504 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2630. Min Range: -6.2630
Max Act: 5.7005. Min Act: -0.1700
Data Index: 5740477 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19