Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 102 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1141. Min Range: -5.1141
Max Act: 5.1141. Min Act: -0.1700
Data Index: 1200817 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.7391. Min Act: -0.1700
Data Index: 698711 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.7703. Min Act: -0.1700
Data Index: 178157 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.8016. Min Act: -0.1700
Data Index: 449228 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.7078. Min Act: -0.1700
Data Index: 1350145 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.6766. Min Act: -0.1700
Data Index: 815426 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.8016. Min Act: -0.1700
Data Index: 1244787 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.7703. Min Act: -0.1700
Data Index: 840191 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.7391. Min Act: -0.1700
Data Index: 496152 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.7703. Min Act: -0.1700
Data Index: 288749 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.7391. Min Act: -0.1700
Data Index: 542950 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.6141. Min Act: -0.1700
Data Index: 387361 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.7391. Min Act: -0.1700
Data Index: 1181889 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.7078. Min Act: -0.1700
Data Index: 1016761 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.7391. Min Act: -0.1700
Data Index: 705946 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.6766. Min Act: -0.1700
Data Index: 1342305 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.6766. Min Act: -0.1700
Data Index: 573709 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.7703. Min Act: -0.1700
Data Index: 497857 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.5828. Min Act: -0.1700
Data Index: 702537 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.6453. Min Act: -0.1700
Data Index: 1285518 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19