Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3926 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.5394. Min Act: -0.0001
Data Index: 729837 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.3560. Min Act: -0.0001
Data Index: 230600 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.2649. Min Act: -0.0001
Data Index: 493440 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.3367. Min Act: -0.0001
Data Index: 1252827 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.2924. Min Act: -0.0001
Data Index: 132406 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.4481. Min Act: -0.0001
Data Index: 902080 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.1991. Min Act: -0.0001
Data Index: 1124445 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.2622. Min Act: -0.0001
Data Index: 610386 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.2578. Min Act: -0.0001
Data Index: 737339 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.0432. Min Act: -0.0001
Data Index: 598082 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.2822. Min Act: -0.0001
Data Index: 118085 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.3794. Min Act: -0.0001
Data Index: 847380 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.1908. Min Act: -0.0001
Data Index: 416672 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.2332. Min Act: -0.0001
Data Index: 1356216 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.2679. Min Act: -0.0001
Data Index: 602975 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.2625. Min Act: -0.0001
Data Index: 380336 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.3619. Min Act: -0.0001
Data Index: 613751 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.0923. Min Act: -0.0001
Data Index: 874891 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.2516. Min Act: -0.0001
Data Index: 52976 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5394. Min Range: -1.5394
Max Act: 1.1535. Min Act: -0.0001
Data Index: 1197121 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19