Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3636 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.0421. Min Act: -0.0001
Data Index: 123355 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.2665. Min Act: -0.0001
Data Index: 638100 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.2441. Min Act: -0.0001
Data Index: 818194 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.2220. Min Act: -0.0001
Data Index: 876143 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.2036. Min Act: -0.0001
Data Index: 1337136 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.2159. Min Act: -0.0001
Data Index: 1239124 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.2090. Min Act: -0.0001
Data Index: 657129 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.2374. Min Act: -0.0001
Data Index: 969335 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.1623. Min Act: -0.0001
Data Index: 383837 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.1500. Min Act: -0.0001
Data Index: 248534 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.0090. Min Act: -0.0001
Data Index: 1134766 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.0584. Min Act: -0.0001
Data Index: 790719 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.1104. Min Act: -0.0001
Data Index: 9140 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.0677. Min Act: -0.0001
Data Index: 389624 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.0177. Min Act: -0.0001
Data Index: 1316452 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.0383. Min Act: -0.0001
Data Index: 1319528 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.1376. Min Act: -0.0001
Data Index: 857499 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.0530. Min Act: -0.0001
Data Index: 545777 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.1201. Min Act: -0.0001
Data Index: 196770 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2665. Min Range: -1.2665
Max Act: 1.0950. Min Act: -0.0001
Data Index: 484306 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19