Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 56 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.8516. Min Act: -0.1700
Data Index: 44186 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.8516. Min Act: -0.1700
Data Index: 1213890 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.8038. Min Act: -0.1700
Data Index: 1329913 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7879. Min Act: -0.1700
Data Index: 740145 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.8038. Min Act: -0.1700
Data Index: 1060151 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.8038. Min Act: -0.1700
Data Index: 1169317 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7879. Min Act: -0.1700
Data Index: 1121049 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7720. Min Act: -0.1700
Data Index: 1351400 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7720. Min Act: -0.1700
Data Index: 1236157 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7879. Min Act: -0.1700
Data Index: 406557 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7560. Min Act: -0.1700
Data Index: 276199 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7401. Min Act: -0.1700
Data Index: 798316 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7401. Min Act: -0.1700
Data Index: 1060800 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7401. Min Act: -0.1700
Data Index: 1329657 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7401. Min Act: -0.1700
Data Index: 577415 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7241. Min Act: -0.1700
Data Index: 844971 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7560. Min Act: -0.1700
Data Index: 24813 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7401. Min Act: -0.1700
Data Index: 155740 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7241. Min Act: -0.1700
Data Index: 111538 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8516. Min Range: -2.8516
Max Act: 2.7241. Min Act: -0.1700
Data Index: 773933 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19