Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1973 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.3254. Min Act: -0.1700
Data Index: 715684 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.3097. Min Act: -0.1700
Data Index: 783975 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.3097. Min Act: -0.1700
Data Index: 335450 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2940. Min Act: -0.1700
Data Index: 429351 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2783. Min Act: -0.1700
Data Index: 449228 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2626. Min Act: -0.1700
Data Index: 30387 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2626. Min Act: -0.1700
Data Index: 62953 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2469. Min Act: -0.1700
Data Index: 960547 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2469. Min Act: -0.1700
Data Index: 604631 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2311. Min Act: -0.1700
Data Index: 458794 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2469. Min Act: -0.1700
Data Index: 822956 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2154. Min Act: -0.1700
Data Index: 238525 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2311. Min Act: -0.1700
Data Index: 397713 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2154. Min Act: -0.1700
Data Index: 717717 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2154. Min Act: -0.1700
Data Index: 1258043 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2154. Min Act: -0.1700
Data Index: 840907 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2154. Min Act: -0.1700
Data Index: 806457 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.1997. Min Act: -0.1700
Data Index: 759791 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2154. Min Act: -0.1700
Data Index: 174326 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3254. Min Range: -3.3254
Max Act: 3.2154. Min Act: -0.1700
Data Index: 725765 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19