Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1976 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1102. Min Range: -4.1102
Max Act: 4.1102. Min Act: -0.1700
Data Index: 283692 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1102. Min Range: -4.1102
Max Act: 4.1102. Min Act: -0.1700
Data Index: 406748 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1102. Min Range: -4.1102
Max Act: 4.0164. Min Act: -0.1700
Data Index: 88112 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1102. Min Range: -4.1102
Max Act: 4.0164. Min Act: -0.1700
Data Index: 816522 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9851. Min Act: -0.1700
Data Index: 165408 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9538. Min Act: -0.1700
Data Index: 1063843 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9851. Min Act: -0.1700
Data Index: 850922 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9851. Min Act: -0.1700
Data Index: 515509 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9851. Min Act: -0.1700
Data Index: 504527 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9538. Min Act: -0.1700
Data Index: 319226 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9851. Min Act: -0.1700
Data Index: 1088913 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9538. Min Act: -0.1700
Data Index: 650385 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9226. Min Act: -0.1700
Data Index: 909443 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9226. Min Act: -0.1700
Data Index: 340232 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9226. Min Act: -0.1700
Data Index: 120402 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.8913. Min Act: -0.1700
Data Index: 452457 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9226. Min Act: -0.1700
Data Index: 412196 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9226. Min Act: -0.1700
Data Index: 218047 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9538. Min Act: -0.1700
Data Index: 608027 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1102. Min Range: -4.1102
Max Act: 3.9226. Min Act: -0.1700
Data Index: 441251 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19