Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2013 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.8247. Min Act: -0.1697
Data Index: 174295 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.6997. Min Act: -0.1700
Data Index: 467808 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.6684. Min Act: -0.1700
Data Index: 141978 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.6997. Min Act: -0.1700
Data Index: 1058932 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.7309. Min Act: -0.1700
Data Index: 283169 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.6684. Min Act: -0.1700
Data Index: 931648 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.6684. Min Act: -0.1700
Data Index: 110281 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.6684. Min Act: -0.1700
Data Index: 493800 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.6372. Min Act: -0.1700
Data Index: 320578 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.6372. Min Act: -0.1698
Data Index: 405428 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.6372. Min Act: -0.1700
Data Index: 1191942 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.6372. Min Act: -0.1700
Data Index: 536738 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.6372. Min Act: -0.1700
Data Index: 1233199 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.6059. Min Act: -0.1700
Data Index: 268680 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.6372. Min Act: -0.1699
Data Index: 1096582 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.5434. Min Act: -0.1700
Data Index: 556834 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.5747. Min Act: -0.1700
Data Index: 1277803 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.5434. Min Act: -0.1700
Data Index: 40095 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.5434. Min Act: -0.1700
Data Index: 20081 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8247. Min Range: -4.8247
Max Act: 4.4809. Min Act: -0.1700
Data Index: 922268 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19