Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 919 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.7994. Min Act: -0.1700
Data Index: 826497 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.6432. Min Act: -0.1700
Data Index: 783201 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.5807. Min Act: -0.1700
Data Index: 190790 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.5807. Min Act: -0.1700
Data Index: 470898 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.5494. Min Act: -0.1700
Data Index: 384960 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.5338. Min Act: -0.1700
Data Index: 1017795 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.5182. Min Act: -0.1700
Data Index: 1177112 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.5182. Min Act: -0.1700
Data Index: 1582578 (Python Code)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.5025. Min Act: -0.1700
Data Index: 1239007 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.4713. Min Act: -0.1700
Data Index: 754923 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.4400. Min Act: -0.1700
Data Index: 1011836 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.4088. Min Act: -0.1700
Data Index: 1574139 (Python Code)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.3931. Min Act: -0.1700
Data Index: 790393 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.3463. Min Act: -0.1700
Data Index: 12333 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.3775. Min Act: -0.1700
Data Index: 1623334 (Python Code)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.3775. Min Act: -0.1700
Data Index: 607200 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.2838. Min Act: -0.1700
Data Index: 335682 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.3150. Min Act: -0.1700
Data Index: 99051 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.2994. Min Act: -0.1700
Data Index: 1103749 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7994. Min Range: -4.7994
Max Act: 4.2994. Min Act: -0.1700
Data Index: 896045 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19