Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2600 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.8722. Min Act: -0.0001
Data Index: 694923 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.8519. Min Act: -0.0001
Data Index: 586258 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.7222. Min Act: -0.0001
Data Index: 897278 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.6680. Min Act: -0.0001
Data Index: 183093 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.6507. Min Act: -0.0001
Data Index: 835308 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.6519. Min Act: -0.0001
Data Index: 844432 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.6334. Min Act: -0.0001
Data Index: 235048 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.5656. Min Act: -0.0001
Data Index: 594127 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.6093. Min Act: -0.0001
Data Index: 757516 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.6110. Min Act: -0.0001
Data Index: 1095938 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.6004. Min Act: -0.0001
Data Index: 544161 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.6010. Min Act: -0.0001
Data Index: 706526 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.5636. Min Act: -0.0001
Data Index: 463028 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.5198. Min Act: -0.0001
Data Index: 786749 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.5504. Min Act: -0.0001
Data Index: 946172 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.5204. Min Act: -0.0001
Data Index: 411956 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.5666. Min Act: -0.0001
Data Index: 589775 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.5032. Min Act: -0.0001
Data Index: 910575 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.5045. Min Act: -0.0001
Data Index: 1165761 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8722. Min Range: -1.8722
Max Act: 1.4977. Min Act: -0.0001
Data Index: 1277953 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19