Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1651 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.7792. Min Act: -0.1700
Data Index: 383576 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.7167. Min Act: -0.1700
Data Index: 922953 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.7479. Min Act: -0.1700
Data Index: 839978 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.7167. Min Act: -0.1700
Data Index: 215566 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.6229. Min Act: -0.1700
Data Index: 275896 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.5917. Min Act: -0.1700
Data Index: 796482 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.5291. Min Act: -0.1700
Data Index: 1143059 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.5604. Min Act: -0.1700
Data Index: 1174564 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.4979. Min Act: -0.1700
Data Index: 272015 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.5291. Min Act: -0.1700
Data Index: 505475 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.5604. Min Act: -0.1700
Data Index: 604197 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.4666. Min Act: -0.1700
Data Index: 942241 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.4979. Min Act: -0.1700
Data Index: 128781 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.3729. Min Act: -0.1700
Data Index: 1229938 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.4354. Min Act: -0.1700
Data Index: 765205 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.4666. Min Act: -0.1700
Data Index: 36165 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.4354. Min Act: -0.1700
Data Index: 717292 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.4041. Min Act: -0.1700
Data Index: 1217931 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.4354. Min Act: -0.1700
Data Index: 482596 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7792. Min Range: -4.7792
Max Act: 4.4041. Min Act: -0.1700
Data Index: 351077 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19