Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1962 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.8019. Min Act: -0.1700
Data Index: 1277931 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.7701. Min Act: -0.1699
Data Index: 16820 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.7381. Min Act: -0.1699
Data Index: 1053717 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.7062. Min Act: -0.1700
Data Index: 1070512 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.7381. Min Act: -0.1700
Data Index: 1304784 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.7222. Min Act: -0.1700
Data Index: 883028 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.7062. Min Act: -0.1698
Data Index: 724137 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.6902. Min Act: -0.1699
Data Index: 1335216 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.6581. Min Act: -0.1700
Data Index: 1086406 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.6421. Min Act: -0.1700
Data Index: 585744 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.6581. Min Act: -0.1700
Data Index: 133857 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.6581. Min Act: -0.1700
Data Index: 941531 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.6581. Min Act: -0.1700
Data Index: 1093024 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.6581. Min Act: -0.1699
Data Index: 184130 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.6421. Min Act: -0.1700
Data Index: 1129180 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.6421. Min Act: -0.1700
Data Index: 636545 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.6421. Min Act: -0.1700
Data Index: 901834 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.6421. Min Act: -0.1700
Data Index: 311806 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.6421. Min Act: -0.1700
Data Index: 1092145 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8019. Min Range: -2.8019
Max Act: 2.6260. Min Act: -0.1700
Data Index: 493614 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19