Model: SoLU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1040 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')
Text #0
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0385. Min Act: -0.0006
Data Index: 1211591 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0327. Min Act: -0.0006
Data Index: 720014 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0318. Min Act: -0.0006
Data Index: 629184 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0310. Min Act: -0.0006
Data Index: 973266 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0315. Min Act: -0.0006
Data Index: 917913 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0301. Min Act: -0.0006
Data Index: 1349413 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0296. Min Act: -0.0006
Data Index: 75473 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0296. Min Act: -0.0006
Data Index: 1078336 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0295. Min Act: -0.0006
Data Index: 1520699 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0293. Min Act: -0.0006
Data Index: 171447 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0286. Min Act: -0.0005
Data Index: 1409135 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0279. Min Act: -0.0006
Data Index: 375088 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0285. Min Act: -0.0006
Data Index: 140093 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0277. Min Act: -0.0006
Data Index: 337271 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0283. Min Act: -0.0006
Data Index: 506505 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0283. Min Act: -0.0006
Data Index: 699248 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0281. Min Act: -0.0005
Data Index: 1016599 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0272. Min Act: -0.0006
Data Index: 596867 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0266. Min Act: -0.0006
Data Index: 321895 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0277. Min Act: -0.0006
Data Index: 961758 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19