Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1079 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.8678. Min Act: -0.1700
Data Index: 949511 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.6490. Min Act: -0.1700
Data Index: 17664 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.6490. Min Act: -0.1700
Data Index: 146071 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.6178. Min Act: -0.1700
Data Index: 260968 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.5865. Min Act: -0.1700
Data Index: 480860 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.5865. Min Act: -0.1700
Data Index: 426399 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.6490. Min Act: -0.1700
Data Index: 122702 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.5553. Min Act: -0.1700
Data Index: 391071 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.5553. Min Act: -0.1700
Data Index: 446379 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.5240. Min Act: -0.1700
Data Index: 1391240 (Python Code)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.4928. Min Act: -0.1700
Data Index: 496136 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.4303. Min Act: -0.1700
Data Index: 1335102 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.5553. Min Act: -0.1700
Data Index: 57478 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.4303. Min Act: -0.1700
Data Index: 862547 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.4928. Min Act: -0.1700
Data Index: 1299639 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.4303. Min Act: -0.1700
Data Index: 677890 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.3678. Min Act: -0.1700
Data Index: 540354 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.3990. Min Act: -0.1700
Data Index: 1523742 (Python Code)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.3678. Min Act: -0.1700
Data Index: 1609311 (Python Code)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8678. Min Range: -6.8678
Max Act: 6.3678. Min Act: -0.1700
Data Index: 1576251 (Python Code)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19