Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2570 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.9351. Min Act: -0.0001
Data Index: 1094286 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.5448. Min Act: -0.0001
Data Index: 958752 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.4830. Min Act: -0.0001
Data Index: 635009 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.5117. Min Act: -0.0001
Data Index: 1627315 (Python Code)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.2689. Min Act: -0.0001
Data Index: 810857 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.2030. Min Act: -0.0001
Data Index: 1265908 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.1707. Min Act: -0.0001
Data Index: 1128707 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.3183. Min Act: -0.0001
Data Index: 726218 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.2890. Min Act: -0.0001
Data Index: 1070746 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.1950. Min Act: -0.0001
Data Index: 1022678 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.1986. Min Act: -0.0001
Data Index: 1190906 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.3209. Min Act: -0.0001
Data Index: 454399 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9351. Min Range: -4.9351
Max Act: 3.9836. Min Act: -0.0001
Data Index: 521933 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.2826. Min Act: -0.0001
Data Index: 1331017 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9351. Min Range: -4.9351
Max Act: 3.9670. Min Act: -0.0001
Data Index: 539680 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9351. Min Range: -4.9351
Max Act: 3.9627. Min Act: -0.0001
Data Index: 468848 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9351. Min Range: -4.9351
Max Act: 3.9576. Min Act: -0.0001
Data Index: 364835 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9351. Min Range: -4.9351
Max Act: 3.9397. Min Act: -0.0001
Data Index: 218629 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.2421. Min Act: -0.0001
Data Index: 210921 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9351. Min Range: -4.9351
Max Act: 4.2494. Min Act: -0.0001
Data Index: 306234 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19