Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 70 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.7256. Min Act: -0.0001
Data Index: 234876 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6373. Min Act: -0.0001
Data Index: 1047991 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.7324. Min Act: -0.0001
Data Index: 1589198 (Python Code)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.7056. Min Act: -0.0001
Data Index: 1386683 (Python Code)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6875. Min Act: -0.0001
Data Index: 188598 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.7040. Min Act: -0.0001
Data Index: 1012436 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6257. Min Act: -0.0001
Data Index: 299803 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.5479. Min Act: -0.0001
Data Index: 450643 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6617. Min Act: -0.0001
Data Index: 431622 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6522. Min Act: -0.0001
Data Index: 698852 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6262. Min Act: -0.0001
Data Index: 1333254 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6009. Min Act: -0.0001
Data Index: 160564 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6541. Min Act: -0.0001
Data Index: 162716 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6336. Min Act: -0.0001
Data Index: 641732 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6329. Min Act: -0.0001
Data Index: 32453 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6890. Min Act: -0.0001
Data Index: 378751 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6089. Min Act: -0.0001
Data Index: 38895 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6096. Min Act: -0.0001
Data Index: 406280 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6382. Min Act: -0.0001
Data Index: 139332 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7324. Min Range: -0.7324
Max Act: 0.6139. Min Act: -0.0001
Data Index: 832946 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19