Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1958 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.9593. Min Act: -0.1700
Data Index: 611683 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.7406. Min Act: -0.1700
Data Index: 972218 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.6156. Min Act: -0.1700
Data Index: 1086041 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.4906. Min Act: -0.1700
Data Index: 486259 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.5843. Min Act: -0.1700
Data Index: 178436 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.3656. Min Act: -0.1700
Data Index: 1011331 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.3656. Min Act: -0.1700
Data Index: 1274021 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.3343. Min Act: -0.1700
Data Index: 135664 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.2093. Min Act: -0.1700
Data Index: 1153572 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.3656. Min Act: -0.1700
Data Index: 469671 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.0843. Min Act: -0.1700
Data Index: 1166816 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.0843. Min Act: -0.1700
Data Index: 1126221 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.0843. Min Act: -0.1700
Data Index: 950030 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9593. Min Range: -6.9593
Max Act: 6.0218. Min Act: -0.1700
Data Index: 83128 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9593. Min Range: -6.9593
Max Act: 5.9906. Min Act: -0.1700
Data Index: 1289632 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9593. Min Range: -6.9593
Max Act: 5.9593. Min Act: -0.1700
Data Index: 652655 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9593. Min Range: -6.9593
Max Act: 5.8968. Min Act: -0.1700
Data Index: 624496 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9593. Min Range: -6.9593
Max Act: 5.9593. Min Act: -0.1700
Data Index: 196885 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9593. Min Range: -6.9593
Max Act: 5.9906. Min Act: -0.1700
Data Index: 216383 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9593. Min Range: -6.9593
Max Act: 5.9281. Min Act: -0.1700
Data Index: 101228 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19