Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1896 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.1972. Min Act: -0.1700
Data Index: 576285 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.1972. Min Act: -0.1700
Data Index: 968496 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.1034. Min Act: -0.1700
Data Index: 1139909 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.1347. Min Act: -0.1700
Data Index: 60054 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.1347. Min Act: -0.1700
Data Index: 686567 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.1034. Min Act: -0.1700
Data Index: 938967 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.1347. Min Act: -0.1700
Data Index: 935638 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.1347. Min Act: -0.1700
Data Index: 923364 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.1034. Min Act: -0.1700
Data Index: 920319 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.1034. Min Act: -0.1700
Data Index: 86800 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.0721. Min Act: -0.1700
Data Index: 476908 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.0409. Min Act: -0.1700
Data Index: 665747 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.0721. Min Act: -0.1700
Data Index: 1330984 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.1034. Min Act: -0.1700
Data Index: 185790 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.0721. Min Act: -0.1700
Data Index: 1038974 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.1034. Min Act: -0.1700
Data Index: 1023228 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.0096. Min Act: -0.1700
Data Index: 1034664 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.0721. Min Act: -0.1700
Data Index: 261476 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.0409. Min Act: -0.1700
Data Index: 421464 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1972. Min Range: -4.1972
Max Act: 4.0409. Min Act: -0.1700
Data Index: 10438 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19