Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2028 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.7033. Min Act: -0.1700
Data Index: 904607 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6713. Min Act: -0.1700
Data Index: 636602 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6552. Min Act: -0.1700
Data Index: 104716 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6552. Min Act: -0.1700
Data Index: 822698 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6392. Min Act: -0.1700
Data Index: 1078662 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6552. Min Act: -0.1700
Data Index: 645447 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6392. Min Act: -0.1700
Data Index: 466883 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6231. Min Act: -0.1700
Data Index: 92167 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6231. Min Act: -0.1700
Data Index: 172334 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6392. Min Act: -0.1700
Data Index: 677484 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6392. Min Act: -0.1700
Data Index: 15338 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6392. Min Act: -0.1700
Data Index: 451101 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6231. Min Act: -0.1700
Data Index: 1540005 (Python Code)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6231. Min Act: -0.1700
Data Index: 1056240 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6231. Min Act: -0.1700
Data Index: 1039924 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6231. Min Act: -0.1700
Data Index: 19124 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6071. Min Act: -0.1700
Data Index: 482067 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6231. Min Act: -0.1700
Data Index: 159373 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6231. Min Act: -0.1700
Data Index: 21893 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7033. Min Range: -2.7033
Max Act: 2.6231. Min Act: -0.1700
Data Index: 486392 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19