Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4365 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.1574. Min Range: -2.1574
Max Act: 2.1574. Min Act: -0.0001
Data Index: 819722 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1574. Min Range: -2.1574
Max Act: 2.0855. Min Act: -0.0001
Data Index: 1081347 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1574. Min Range: -2.1574
Max Act: 2.0173. Min Act: -0.0001
Data Index: 1443530 (Python Code)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.8053. Min Act: -0.0001
Data Index: 1024561 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.6271. Min Act: -0.0001
Data Index: 107655 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.6236. Min Act: -0.0001
Data Index: 1346712 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.7662. Min Act: -0.0001
Data Index: 290419 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.6751. Min Act: -0.0001
Data Index: 667927 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.7223. Min Act: -0.0001
Data Index: 129762 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.6741. Min Act: -0.0001
Data Index: 124454 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1574. Min Range: -2.1574
Max Act: 2.0200. Min Act: -0.0001
Data Index: 357678 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.5391. Min Act: -0.0001
Data Index: 849343 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.6832. Min Act: -0.0001
Data Index: 985206 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.6582. Min Act: -0.0001
Data Index: 250299 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.4611. Min Act: -0.0001
Data Index: 302986 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.6440. Min Act: -0.0001
Data Index: 1052289 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.5078. Min Act: -0.0001
Data Index: 522577 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.3367. Min Act: -0.0001
Data Index: 417715 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.5910. Min Act: -0.0001
Data Index: 535278 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1574. Min Range: -2.1574
Max Act: 1.8265. Min Act: -0.0001
Data Index: 994827 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19