Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 608 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0307. Min Act: -0.0001
Data Index: 996700 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0285. Min Act: -0.0001
Data Index: 314462 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0290. Min Act: -0.0001
Data Index: 701533 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0252. Min Act: -0.0001
Data Index: 239917 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0262. Min Act: -0.0001
Data Index: 17194 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0255. Min Act: -0.0001
Data Index: 92318 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0199. Min Act: -0.0001
Data Index: 648591 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0250. Min Act: -0.0001
Data Index: 707981 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0239. Min Act: -0.0001
Data Index: 439949 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0243. Min Act: -0.0001
Data Index: 852986 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0243. Min Act: -0.0001
Data Index: 332879 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0226. Min Act: -0.0001
Data Index: 1281606 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0219. Min Act: -0.0001
Data Index: 543820 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0234. Min Act: -0.0001
Data Index: 777304 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0221. Min Act: -0.0001
Data Index: 575421 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0213. Min Act: -0.0001
Data Index: 1325563 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0222. Min Act: -0.0001
Data Index: 1244522 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0219. Min Act: -0.0001
Data Index: 60326 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0207. Min Act: -0.0001
Data Index: 1281037 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0307. Min Range: -0.0307
Max Act: 0.0220. Min Act: -0.0001
Data Index: 662885 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19