Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2590 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.6882. Min Act: -0.0001
Data Index: 1161540 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.4818. Min Act: -0.0001
Data Index: 267174 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.3863. Min Act: -0.0001
Data Index: 742541 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.2337. Min Act: -0.0001
Data Index: 399928 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.2443. Min Act: -0.0001
Data Index: 1136802 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.2212. Min Act: -0.0001
Data Index: 605384 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.1681. Min Act: -0.0001
Data Index: 389892 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.1674. Min Act: -0.0001
Data Index: 1247416 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.1248. Min Act: -0.0001
Data Index: 1137567 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.1987. Min Act: -0.0001
Data Index: 767293 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.1575. Min Act: -0.0001
Data Index: 755914 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.0954. Min Act: -0.0001
Data Index: 1155970 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.1187. Min Act: -0.0001
Data Index: 572404 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.1210. Min Act: -0.0001
Data Index: 761125 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.0780. Min Act: -0.0001
Data Index: 1316922 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6882. Min Range: -1.6882
Max Act: 0.9743. Min Act: -0.0001
Data Index: 441576 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.0891. Min Act: -0.0001
Data Index: 664732 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.1446. Min Act: -0.0001
Data Index: 1117323 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.0535. Min Act: -0.0001
Data Index: 363979 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6882. Min Range: -1.6882
Max Act: 1.0147. Min Act: -0.0001
Data Index: 1352347 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19