Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 584 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.8707. Min Act: -0.1700
Data Index: 76394 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.8389. Min Act: -0.1700
Data Index: 245640 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.8230. Min Act: -0.1700
Data Index: 101027 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7911. Min Act: -0.1700
Data Index: 1349535 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7752. Min Act: -0.1700
Data Index: 45683 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7911. Min Act: -0.1700
Data Index: 226177 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7752. Min Act: -0.1700
Data Index: 101068 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7433. Min Act: -0.1700
Data Index: 720216 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7433. Min Act: -0.1700
Data Index: 1191381 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7592. Min Act: -0.1700
Data Index: 1331727 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7592. Min Act: -0.1700
Data Index: 974481 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7273. Min Act: -0.1700
Data Index: 852208 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7273. Min Act: -0.1700
Data Index: 723761 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7273. Min Act: -0.1700
Data Index: 234999 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7273. Min Act: -0.1700
Data Index: 171621 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7113. Min Act: -0.1700
Data Index: 1010595 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.6953. Min Act: -0.1700
Data Index: 922907 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7113. Min Act: -0.1700
Data Index: 745926 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.7113. Min Act: -0.1700
Data Index: 215012 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8707. Min Range: -2.8707
Max Act: 2.6953. Min Act: -0.1700
Data Index: 1020555 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19