Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 129 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.6925. Min Act: -0.1700
Data Index: 1234338 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.6604. Min Act: -0.1700
Data Index: 325411 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.6283. Min Act: -0.1700
Data Index: 255682 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.6283. Min Act: -0.1700
Data Index: 545621 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.6283. Min Act: -0.1700
Data Index: 952474 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.6123. Min Act: -0.1700
Data Index: 170459 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5962. Min Act: -0.1700
Data Index: 415952 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5801. Min Act: -0.1700
Data Index: 340491 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5801. Min Act: -0.1700
Data Index: 835652 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5801. Min Act: -0.1700
Data Index: 76486 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5801. Min Act: -0.1700
Data Index: 405265 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5962. Min Act: -0.1700
Data Index: 170635 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5962. Min Act: -0.1700
Data Index: 1041336 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5962. Min Act: -0.1700
Data Index: 321835 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5639. Min Act: -0.1700
Data Index: 10245 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5478. Min Act: -0.1700
Data Index: 206351 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5478. Min Act: -0.1700
Data Index: 828807 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5478. Min Act: -0.1700
Data Index: 635608 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5317. Min Act: -0.1700
Data Index: 550892 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6925. Min Range: -2.6925
Max Act: 2.5317. Min Act: -0.1700
Data Index: 414949 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19