Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 15 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.8344. Min Act: -0.1700
Data Index: 1210043 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.7719. Min Act: -0.1700
Data Index: 81878 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.7094. Min Act: -0.1700
Data Index: 106306 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.7094. Min Act: -0.1700
Data Index: 1288581 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.7406. Min Act: -0.1700
Data Index: 419794 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.6781. Min Act: -0.1700
Data Index: 929563 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.6312. Min Act: -0.1700
Data Index: 497294 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.5843. Min Act: -0.1700
Data Index: 150229 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.6312. Min Act: -0.1700
Data Index: 448836 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.6312. Min Act: -0.1700
Data Index: 400117 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.6468. Min Act: -0.1700
Data Index: 1016278 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.5687. Min Act: -0.1700
Data Index: 1087521 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.5843. Min Act: -0.1700
Data Index: 774333 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.6156. Min Act: -0.1700
Data Index: 529404 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.5843. Min Act: -0.1700
Data Index: 43218 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.6156. Min Act: -0.1700
Data Index: 313332 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.6312. Min Act: -0.1700
Data Index: 146206 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.5531. Min Act: -0.1700
Data Index: 1091947 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.5843. Min Act: -0.1700
Data Index: 884564 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8344. Min Range: -4.8344
Max Act: 4.6312. Min Act: -0.1700
Data Index: 161257 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19