Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 57 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.6843. Min Act: -0.1700
Data Index: 702611 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.6201. Min Act: -0.1700
Data Index: 978569 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.6201. Min Act: -0.1700
Data Index: 302071 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.6040. Min Act: -0.1700
Data Index: 259618 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5880. Min Act: -0.1700
Data Index: 1357672 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5880. Min Act: -0.1700
Data Index: 313562 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5234. Min Act: -0.1700
Data Index: 500525 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5557. Min Act: -0.1700
Data Index: 1081728 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5557. Min Act: -0.1700
Data Index: 479616 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5396. Min Act: -0.1700
Data Index: 626946 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5557. Min Act: -0.1700
Data Index: 1281028 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5557. Min Act: -0.1700
Data Index: 59642 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5396. Min Act: -0.1700
Data Index: 7397 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5396. Min Act: -0.1700
Data Index: 47352 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5718. Min Act: -0.1700
Data Index: 667049 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5072. Min Act: -0.1700
Data Index: 615856 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5234. Min Act: -0.1700
Data Index: 1208482 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5396. Min Act: -0.1700
Data Index: 915883 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5072. Min Act: -0.1700
Data Index: 588506 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6843. Min Range: -2.6843
Max Act: 2.5234. Min Act: -0.1700
Data Index: 670978 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19