Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1868 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.1112. Min Range: -3.1112
Max Act: 3.1112. Min Act: -0.1700
Data Index: 1200559 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1112. Min Range: -3.1112
Max Act: 3.0638. Min Act: -0.1700
Data Index: 375886 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1112. Min Range: -3.1112
Max Act: 3.0323. Min Act: -0.1700
Data Index: 896618 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1112. Min Range: -3.1112
Max Act: 3.0165. Min Act: -0.1700
Data Index: 804288 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1112. Min Range: -3.1112
Max Act: 3.0007. Min Act: -0.1700
Data Index: 396855 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.9690. Min Act: -0.1700
Data Index: 1269305 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.9690. Min Act: -0.1700
Data Index: 579007 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.9374. Min Act: -0.1700
Data Index: 1100525 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.9215. Min Act: -0.1700
Data Index: 1252461 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.9057. Min Act: -0.1700
Data Index: 886582 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.8898. Min Act: -0.1700
Data Index: 280156 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.9057. Min Act: -0.1700
Data Index: 99224 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.8739. Min Act: -0.1700
Data Index: 57516 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.8580. Min Act: -0.1700
Data Index: 654410 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.8739. Min Act: -0.1700
Data Index: 132566 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.8580. Min Act: -0.1700
Data Index: 274111 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.8580. Min Act: -0.1700
Data Index: 706335 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.8422. Min Act: -0.1700
Data Index: 138564 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.8422. Min Act: -0.1700
Data Index: 799052 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1112. Min Range: -3.1112
Max Act: 2.8580. Min Act: -0.1700
Data Index: 645794 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19