Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4512 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 6.0728. Min Range: -6.0728
Max Act: 5.8511. Min Act: -0.0001
Data Index: 85640 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0728. Min Range: -6.0728
Max Act: 5.6744. Min Act: -0.0001
Data Index: 891465 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0728. Min Range: -6.0728
Max Act: 6.0728. Min Act: -0.0001
Data Index: 1159174 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0728. Min Range: -6.0728
Max Act: 5.6301. Min Act: -0.0001
Data Index: 1123677 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0728. Min Range: -6.0728
Max Act: 5.2086. Min Act: -0.0001
Data Index: 341406 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0728. Min Range: -6.0728
Max Act: 5.5400. Min Act: -0.0001
Data Index: 615188 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0728. Min Range: -6.0728
Max Act: 5.3156. Min Act: -0.0001
Data Index: 878496 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0728. Min Range: -6.0728
Max Act: 5.4195. Min Act: -0.0001
Data Index: 884316 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0728. Min Range: -6.0728
Max Act: 5.2272. Min Act: -0.0001
Data Index: 767317 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0728. Min Range: -6.0728
Max Act: 5.3395. Min Act: -0.0001
Data Index: 646897 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0728. Min Range: -6.0728
Max Act: 4.8996. Min Act: -0.0001
Data Index: 484580 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0728. Min Range: -6.0728
Max Act: 4.9743. Min Act: -0.0001
Data Index: 1094960 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0728. Min Range: -6.0728
Max Act: 4.3560. Min Act: -0.0001
Data Index: 632164 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0728. Min Range: -6.0728
Max Act: 4.5429. Min Act: -0.0001
Data Index: 338521 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0728. Min Range: -6.0728
Max Act: 4.8911. Min Act: -0.0001
Data Index: 774792 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0728. Min Range: -6.0728
Max Act: 4.5914. Min Act: -0.0001
Data Index: 65192 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0728. Min Range: -6.0728
Max Act: 4.5628. Min Act: -0.0001
Data Index: 999106 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0728. Min Range: -6.0728
Max Act: 4.8962. Min Act: -0.0001
Data Index: 961187 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0728. Min Range: -6.0728
Max Act: 4.8661. Min Act: -0.0001
Data Index: 1067548 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0728. Min Range: -6.0728
Max Act: 4.6424. Min Act: -0.0001
Data Index: 34959 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19