Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1997 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.7641. Min Act: -0.1700
Data Index: 1079659 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.7485. Min Act: -0.1700
Data Index: 28699 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.5766. Min Act: -0.1700
Data Index: 556081 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.5766. Min Act: -0.1700
Data Index: 1206258 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.5766. Min Act: -0.1700
Data Index: 856054 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.5766. Min Act: -0.1700
Data Index: 489131 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.5610. Min Act: -0.1700
Data Index: 770211 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.5141. Min Act: -0.1700
Data Index: 670679 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.5141. Min Act: -0.1700
Data Index: 1145985 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.4985. Min Act: -0.1700
Data Index: 20528 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.5297. Min Act: -0.1700
Data Index: 1106989 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.5453. Min Act: -0.1700
Data Index: 63579 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.5297. Min Act: -0.1700
Data Index: 941332 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.4516. Min Act: -0.1700
Data Index: 49749 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.4516. Min Act: -0.1700
Data Index: 668671 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.4828. Min Act: -0.1700
Data Index: 974283 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.4828. Min Act: -0.1700
Data Index: 1141335 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.4516. Min Act: -0.1700
Data Index: 213722 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.4672. Min Act: -0.1700
Data Index: 697018 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7641. Min Range: -4.7641
Max Act: 4.3891. Min Act: -0.1700
Data Index: 973603 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19