Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1499 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.3236. Min Act: -0.1700
Data Index: 1046204 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.2924. Min Act: -0.1700
Data Index: 261414 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.2924. Min Act: -0.1700
Data Index: 1129801 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.2611. Min Act: -0.1700
Data Index: 275615 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.2611. Min Act: -0.1700
Data Index: 603974 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.2611. Min Act: -0.1700
Data Index: 1208824 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.2924. Min Act: -0.1700
Data Index: 640575 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.2299. Min Act: -0.1700
Data Index: 1201056 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.2299. Min Act: -0.1700
Data Index: 443547 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.1986. Min Act: -0.1700
Data Index: 506155 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.2299. Min Act: -0.1700
Data Index: 52580 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.1986. Min Act: -0.1700
Data Index: 999125 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.2611. Min Act: -0.1700
Data Index: 962655 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.1986. Min Act: -0.1700
Data Index: 673843 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.1674. Min Act: -0.1700
Data Index: 479976 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.1986. Min Act: -0.1700
Data Index: 476999 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.1986. Min Act: -0.1700
Data Index: 441645 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.1361. Min Act: -0.1700
Data Index: 797596 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.1674. Min Act: -0.1700
Data Index: 916339 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3236. Min Range: -4.3236
Max Act: 4.1674. Min Act: -0.1700
Data Index: 916870 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19