Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1982 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.2642. Min Act: -0.1700
Data Index: 936205 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.2955. Min Act: -0.1700
Data Index: 484039 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.3111. Min Act: -0.1700
Data Index: 860685 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.2486. Min Act: -0.1700
Data Index: 347913 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.2173. Min Act: -0.1700
Data Index: 1156482 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.2017. Min Act: -0.1700
Data Index: 1017089 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.2017. Min Act: -0.1700
Data Index: 1334769 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.2173. Min Act: -0.1700
Data Index: 735669 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.1861. Min Act: -0.1700
Data Index: 1059106 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.1704. Min Act: -0.1700
Data Index: 1356595 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.1235. Min Act: -0.1700
Data Index: 447638 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.1704. Min Act: -0.1700
Data Index: 658484 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.1548. Min Act: -0.1700
Data Index: 1066001 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.1392. Min Act: -0.1700
Data Index: 435191 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.1392. Min Act: -0.1700
Data Index: 493782 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.1548. Min Act: -0.1700
Data Index: 968617 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.1548. Min Act: -0.1700
Data Index: 1271163 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.1079. Min Act: -0.1700
Data Index: 1167691 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.1235. Min Act: -0.1700
Data Index: 1060982 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3111. Min Range: -4.3111
Max Act: 4.1548. Min Act: -0.1700
Data Index: 821755 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19