Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2021 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1152. Min Range: -4.1152
Max Act: 4.1152. Min Act: -0.1700
Data Index: 1257318 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.9589. Min Act: -0.1700
Data Index: 46626 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.9589. Min Act: -0.1700
Data Index: 1212726 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.9276. Min Act: -0.1700
Data Index: 1359339 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.9276. Min Act: -0.1700
Data Index: 290836 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.9276. Min Act: -0.1700
Data Index: 1300461 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.8964. Min Act: -0.1700
Data Index: 788104 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.8964. Min Act: -0.1700
Data Index: 1274594 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.8651. Min Act: -0.1700
Data Index: 178015 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.8964. Min Act: -0.1700
Data Index: 1214069 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.8338. Min Act: -0.1700
Data Index: 505839 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.8338. Min Act: -0.1700
Data Index: 673915 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.8651. Min Act: -0.1700
Data Index: 1098362 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.8338. Min Act: -0.1700
Data Index: 893403 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.8338. Min Act: -0.1700
Data Index: 55519 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.7713. Min Act: -0.1700
Data Index: 431661 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.8025. Min Act: -0.1700
Data Index: 851759 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.8025. Min Act: -0.1700
Data Index: 409160 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.8338. Min Act: -0.1700
Data Index: 294939 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1152. Min Range: -4.1152
Max Act: 3.8338. Min Act: -0.1700
Data Index: 396197 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19