Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1737 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.1256. Min Range: -4.1256
Max Act: 4.1256. Min Act: -0.1700
Data Index: 984592 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1256. Min Range: -4.1256
Max Act: 4.0318. Min Act: -0.1700
Data Index: 392585 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1256. Min Range: -4.1256
Max Act: 4.0005. Min Act: -0.1700
Data Index: 903839 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1256. Min Range: -4.1256
Max Act: 4.0005. Min Act: -0.1700
Data Index: 543508 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.9380. Min Act: -0.1700
Data Index: 1475506 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.9380. Min Act: -0.1700
Data Index: 1099003 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.9693. Min Act: -0.1700
Data Index: 342175 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.8754. Min Act: -0.1700
Data Index: 793731 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.9067. Min Act: -0.1700
Data Index: 779506 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.8754. Min Act: -0.1700
Data Index: 36725 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.9067. Min Act: -0.1700
Data Index: 89748 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.8754. Min Act: -0.1700
Data Index: 1646959 (Python Code)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.8754. Min Act: -0.1700
Data Index: 1380570 (Python Code)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.8754. Min Act: -0.1700
Data Index: 204152 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.8754. Min Act: -0.1700
Data Index: 75989 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.9067. Min Act: -0.1700
Data Index: 1279565 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.9067. Min Act: -0.1700
Data Index: 9700 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.8754. Min Act: -0.1700
Data Index: 1191729 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.8442. Min Act: -0.1700
Data Index: 431344 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1256. Min Range: -4.1256
Max Act: 3.8442. Min Act: -0.1700
Data Index: 906637 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19