Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 575 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6831. Min Act: -0.1700
Data Index: 550656 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6987. Min Act: -0.1700
Data Index: 454800 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6987. Min Act: -0.1700
Data Index: 1472533 (Python Code)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.7144. Min Act: -0.1700
Data Index: 1248399 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.7144. Min Act: -0.1700
Data Index: 946093 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.7300. Min Act: -0.1700
Data Index: 404724 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.7144. Min Act: -0.1700
Data Index: 551456 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6987. Min Act: -0.1700
Data Index: 746755 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6987. Min Act: -0.1700
Data Index: 1357850 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6675. Min Act: -0.1700
Data Index: 230968 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6675. Min Act: -0.1700
Data Index: 260779 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6519. Min Act: -0.1700
Data Index: 842281 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6987. Min Act: -0.1700
Data Index: 919797 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6519. Min Act: -0.1700
Data Index: 1043468 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6519. Min Act: -0.1700
Data Index: 408493 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6675. Min Act: -0.1700
Data Index: 1020665 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6987. Min Act: -0.1700
Data Index: 33038 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6519. Min Act: -0.1700
Data Index: 206775 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6206. Min Act: -0.1700
Data Index: 205680 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7300. Min Range: -4.7300
Max Act: 4.6519. Min Act: -0.1700
Data Index: 1231140 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19