Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 177 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8842. Min Act: -0.1700
Data Index: 716569 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8842. Min Act: -0.1700
Data Index: 746682 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8683. Min Act: -0.1700
Data Index: 126649 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8365. Min Act: -0.1700
Data Index: 625866 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8365. Min Act: -0.1700
Data Index: 680273 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8365. Min Act: -0.1700
Data Index: 1114566 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8365. Min Act: -0.1700
Data Index: 60230 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8047. Min Act: -0.1700
Data Index: 1266538 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8206. Min Act: -0.1700
Data Index: 688797 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8206. Min Act: -0.1700
Data Index: 563630 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8047. Min Act: -0.1700
Data Index: 640684 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8047. Min Act: -0.1700
Data Index: 749440 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8047. Min Act: -0.1700
Data Index: 598978 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.7888. Min Act: -0.1700
Data Index: 1280500 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.7728. Min Act: -0.1700
Data Index: 758442 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.7888. Min Act: -0.1700
Data Index: 206486 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.7888. Min Act: -0.1700
Data Index: 377327 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.7888. Min Act: -0.1700
Data Index: 755114 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.8047. Min Act: -0.1700
Data Index: 647589 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8842. Min Range: -2.8842
Max Act: 2.7888. Min Act: -0.1700
Data Index: 712663 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19