Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2010 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0340. Min Act: -0.0001
Data Index: 1112829 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0321. Min Act: -0.0001
Data Index: 146426 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0328. Min Act: -0.0001
Data Index: 989149 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0373. Min Act: -0.0001
Data Index: 947278 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0305. Min Act: -0.0001
Data Index: 1170478 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0330. Min Act: -0.0001
Data Index: 1130316 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0326. Min Act: -0.0001
Data Index: 517743 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0333. Min Act: -0.0001
Data Index: 1243689 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0320. Min Act: -0.0001
Data Index: 971282 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0291. Min Act: -0.0001
Data Index: 1045808 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0269. Min Act: -0.0001
Data Index: 345216 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0287. Min Act: -0.0001
Data Index: 752971 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0293. Min Act: -0.0001
Data Index: 1277168 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0304. Min Act: -0.0001
Data Index: 263898 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0275. Min Act: -0.0001
Data Index: 133875 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0283. Min Act: -0.0001
Data Index: 506601 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0256. Min Act: -0.0001
Data Index: 397787 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0258. Min Act: -0.0001
Data Index: 1126115 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0258. Min Act: -0.0001
Data Index: 1018087 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0373. Min Range: -0.0373
Max Act: 0.0266. Min Act: -0.0001
Data Index: 907334 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19