Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1566 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.7966. Min Act: -0.1700
Data Index: 940294 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.7488. Min Act: -0.1700
Data Index: 1121437 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.7488. Min Act: -0.1700
Data Index: 505780 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.7488. Min Act: -0.1700
Data Index: 247321 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.7488. Min Act: -0.1700
Data Index: 1014454 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.7488. Min Act: -0.1700
Data Index: 927307 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.7009. Min Act: -0.1700
Data Index: 895519 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.6849. Min Act: -0.1700
Data Index: 863063 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.6688. Min Act: -0.1700
Data Index: 1122435 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.6688. Min Act: -0.1700
Data Index: 1039199 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.6688. Min Act: -0.1700
Data Index: 210967 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.6688. Min Act: -0.1700
Data Index: 168582 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.6688. Min Act: -0.1700
Data Index: 1134674 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.6688. Min Act: -0.1700
Data Index: 1342668 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.6528. Min Act: -0.1700
Data Index: 16289 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.6528. Min Act: -0.1700
Data Index: 399792 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.6367. Min Act: -0.1700
Data Index: 1244431 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.6688. Min Act: -0.1700
Data Index: 227219 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.6367. Min Act: -0.1700
Data Index: 1172981 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7966. Min Range: -2.7966
Max Act: 2.6367. Min Act: -0.1700
Data Index: 397710 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19