Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 9 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0397. Min Range: -4.0397
Max Act: 4.0397. Min Act: -0.1700
Data Index: 1294698 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.9772. Min Act: -0.1700
Data Index: 335466 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.8833. Min Act: -0.1700
Data Index: 539249 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.7895. Min Act: -0.1700
Data Index: 1065911 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.8208. Min Act: -0.1700
Data Index: 1172515 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.8208. Min Act: -0.1700
Data Index: 817613 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.7582. Min Act: -0.1700
Data Index: 244462 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.8208. Min Act: -0.1700
Data Index: 627235 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.7895. Min Act: -0.1700
Data Index: 366730 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.7895. Min Act: -0.1700
Data Index: 652484 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.7895. Min Act: -0.1700
Data Index: 219211 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.7582. Min Act: -0.1700
Data Index: 867475 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.7582. Min Act: -0.1700
Data Index: 360473 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.7582. Min Act: -0.1700
Data Index: 107826 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.7269. Min Act: -0.1700
Data Index: 491313 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.7582. Min Act: -0.1700
Data Index: 609836 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.7895. Min Act: -0.1700
Data Index: 146265 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.6956. Min Act: -0.1700
Data Index: 335419 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.7269. Min Act: -0.1700
Data Index: 1257492 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0397. Min Range: -4.0397
Max Act: 3.7269. Min Act: -0.1700
Data Index: 1261131 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19