Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5416 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.2599. Min Act: -0.0001
Data Index: 588940 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0728. Min Act: -0.0001
Data Index: 903541 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0589. Min Act: -0.0001
Data Index: 1224628 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0686. Min Act: -0.0001
Data Index: 747114 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0433. Min Act: -0.0001
Data Index: 358068 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0398. Min Act: -0.0001
Data Index: 349581 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0318. Min Act: -0.0001
Data Index: 967936 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0289. Min Act: -0.0001
Data Index: 829444 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0251. Min Act: -0.0001
Data Index: 440173 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0263. Min Act: -0.0001
Data Index: 476265 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0285. Min Act: -0.0001
Data Index: 1338536 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0248. Min Act: -0.0001
Data Index: 1457685 (Python Code)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0239. Min Act: -0.0001
Data Index: 728551 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0245. Min Act: -0.0001
Data Index: 1042070 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0235. Min Act: -0.0001
Data Index: 1270039 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0240. Min Act: -0.0001
Data Index: 11321 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0220. Min Act: -0.0001
Data Index: 1008108 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0213. Min Act: -0.0001
Data Index: 165302 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0220. Min Act: -0.0001
Data Index: 1011115 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2599. Min Range: -0.2599
Max Act: 0.0228. Min Act: -0.0001
Data Index: 1476870 (Python Code)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19