Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 82 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.5122. Min Act: -0.1700
Data Index: 788977 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.5122. Min Act: -0.1700
Data Index: 337928 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.4960. Min Act: -0.1700
Data Index: 234937 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.4960. Min Act: -0.1700
Data Index: 1054949 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.4636. Min Act: -0.1700
Data Index: 573519 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.4636. Min Act: -0.1700
Data Index: 492772 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.4473. Min Act: -0.1700
Data Index: 247509 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.4311. Min Act: -0.1700
Data Index: 1221612 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.4311. Min Act: -0.1700
Data Index: 565306 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.4311. Min Act: -0.1700
Data Index: 486005 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.4148. Min Act: -0.1700
Data Index: 25786 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.4148. Min Act: -0.1700
Data Index: 1304478 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.4148. Min Act: -0.1700
Data Index: 989969 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.3821. Min Act: -0.1700
Data Index: 362366 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.4148. Min Act: -0.1700
Data Index: 73391 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.3985. Min Act: -0.1700
Data Index: 1347316 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.3985. Min Act: -0.1700
Data Index: 1231901 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.3821. Min Act: -0.1700
Data Index: 1015032 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.3985. Min Act: -0.1700
Data Index: 1354715 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5122. Min Range: -2.5122
Max Act: 2.3821. Min Act: -0.1700
Data Index: 276285 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19