Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4795 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.8604. Min Act: -0.1700
Data Index: 2552477 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.8291. Min Act: -0.1700
Data Index: 7797216 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.7979. Min Act: -0.1700
Data Index: 6888699 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.7666. Min Act: -0.1700
Data Index: 3325446 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.6729. Min Act: -0.1700
Data Index: 8719185 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.6729. Min Act: -0.1700
Data Index: 5345786 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.6416. Min Act: -0.1700
Data Index: 4998790 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.6416. Min Act: -0.1700
Data Index: 36067 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.6104. Min Act: -0.1700
Data Index: 345544 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.6104. Min Act: -0.1700
Data Index: 6522701 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.6104. Min Act: -0.1700
Data Index: 2222503 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.5791. Min Act: -0.1700
Data Index: 7658282 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.5791. Min Act: -0.1700
Data Index: 5480127 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.5479. Min Act: -0.1700
Data Index: 6633103 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.5791. Min Act: -0.1700
Data Index: 3726913 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.5479. Min Act: -0.1700
Data Index: 3203175 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.5479. Min Act: -0.1700
Data Index: 1597614 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.5166. Min Act: -0.1700
Data Index: 4907219 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.5166. Min Act: -0.1700
Data Index: 1726146 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.5166. Min Act: -0.1700
Data Index: 1864839 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19