Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1744 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.1037. Min Range: -6.1037
Max Act: 6.1037. Min Act: -0.1700
Data Index: 568753 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1037. Min Range: -6.1037
Max Act: 6.0412. Min Act: -0.1700
Data Index: 1214660 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1037. Min Range: -6.1037
Max Act: 6.0412. Min Act: -0.1700
Data Index: 281134 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.9787. Min Act: -0.1700
Data Index: 765345 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.9475. Min Act: -0.1700
Data Index: 1082688 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.9787. Min Act: -0.1700
Data Index: 881164 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.9475. Min Act: -0.1700
Data Index: 1059707 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.8850. Min Act: -0.1700
Data Index: 1358370 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.9162. Min Act: -0.1700
Data Index: 570818 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.9162. Min Act: -0.1700
Data Index: 395902 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.8850. Min Act: -0.1700
Data Index: 78290 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.8537. Min Act: -0.1700
Data Index: 222628 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.8225. Min Act: -0.1700
Data Index: 431759 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.8537. Min Act: -0.1700
Data Index: 1021391 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.7912. Min Act: -0.1700
Data Index: 954186 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.8225. Min Act: -0.1700
Data Index: 380923 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.7912. Min Act: -0.1700
Data Index: 191580 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.7912. Min Act: -0.1700
Data Index: 407002 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.7600. Min Act: -0.1700
Data Index: 703505 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1037. Min Range: -6.1037
Max Act: 5.7287. Min Act: -0.1700
Data Index: 821947 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19