Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2041 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1504. Min Range: -4.1504
Max Act: 4.1504. Min Act: -0.1700
Data Index: 3751 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1504. Min Range: -4.1504
Max Act: 4.0566. Min Act: -0.1700
Data Index: 719772 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1504. Min Range: -4.1504
Max Act: 4.0254. Min Act: -0.1700
Data Index: 949857 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1504. Min Range: -4.1504
Max Act: 4.0879. Min Act: -0.1700
Data Index: 99449 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1504. Min Range: -4.1504
Max Act: 4.0254. Min Act: -0.1700
Data Index: 113045 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.9941. Min Act: -0.1700
Data Index: 87882 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1504. Min Range: -4.1504
Max Act: 4.0254. Min Act: -0.1700
Data Index: 185944 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.9941. Min Act: -0.1700
Data Index: 400848 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.9941. Min Act: -0.1700
Data Index: 133661 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.9941. Min Act: -0.1700
Data Index: 543044 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.9941. Min Act: -0.1700
Data Index: 1091904 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.9941. Min Act: -0.1700
Data Index: 997131 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.9941. Min Act: -0.1700
Data Index: 1047759 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.9941. Min Act: -0.1700
Data Index: 826869 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.8690. Min Act: -0.1700
Data Index: 544742 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.9628. Min Act: -0.1700
Data Index: 489802 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.9316. Min Act: -0.1700
Data Index: 1094152 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.9003. Min Act: -0.1700
Data Index: 599758 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.9003. Min Act: -0.1700
Data Index: 718341 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1504. Min Range: -4.1504
Max Act: 3.9628. Min Act: -0.1700
Data Index: 467645 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19