Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1191 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.7357. Min Act: -0.1700
Data Index: 168691 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.7198. Min Act: -0.1700
Data Index: 1119227 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.6717. Min Act: -0.1700
Data Index: 244167 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.6557. Min Act: -0.1700
Data Index: 735605 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.6557. Min Act: -0.1700
Data Index: 804221 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.6397. Min Act: -0.1700
Data Index: 469218 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.6236. Min Act: -0.1700
Data Index: 848671 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.6075. Min Act: -0.1700
Data Index: 801094 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.6236. Min Act: -0.1700
Data Index: 325386 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.6236. Min Act: -0.1700
Data Index: 501107 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.6397. Min Act: -0.1700
Data Index: 816851 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.5914. Min Act: -0.1700
Data Index: 1187917 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.5914. Min Act: -0.1700
Data Index: 67003 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.5914. Min Act: -0.1700
Data Index: 693490 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.5914. Min Act: -0.1700
Data Index: 525147 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.6075. Min Act: -0.1700
Data Index: 1276163 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.5914. Min Act: -0.1700
Data Index: 194834 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.5914. Min Act: -0.1700
Data Index: 558579 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.5914. Min Act: -0.1700
Data Index: 576911 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7357. Min Range: -2.7357
Max Act: 2.5753. Min Act: -0.1700
Data Index: 440709 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19