Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5173 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.4973. Min Act: -0.0001
Data Index: 1086574 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.3853. Min Act: -0.0001
Data Index: 96669 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.6025. Min Act: -0.0001
Data Index: 185639 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.4444. Min Act: -0.0001
Data Index: 350629 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.4198. Min Act: -0.0001
Data Index: 155058 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.4607. Min Act: -0.0001
Data Index: 915351 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.2897. Min Act: -0.0001
Data Index: 1355439 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.2099. Min Act: -0.0001
Data Index: 732384 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.2071. Min Act: -0.0001
Data Index: 125900 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.4259. Min Act: -0.0001
Data Index: 714456 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.3084. Min Act: -0.0001
Data Index: 334496 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.2582. Min Act: -0.0001
Data Index: 421945 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.1791. Min Act: -0.0001
Data Index: 431549 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.2346. Min Act: -0.0001
Data Index: 421854 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.1596. Min Act: -0.0001
Data Index: 152083 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.2327. Min Act: -0.0001
Data Index: 166530 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.1378. Min Act: -0.0001
Data Index: 45390 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.1655. Min Act: -0.0001
Data Index: 33696 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.0651. Min Act: -0.0001
Data Index: 459649 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6025. Min Range: -1.6025
Max Act: 1.0582. Min Act: -0.0001
Data Index: 1586980 (Python Code)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19