Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2907 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.4346. Min Act: -0.0001
Data Index: 234957 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.3199. Min Act: -0.0001
Data Index: 1258266 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.4346. Min Act: -0.0001
Data Index: 857839 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.3309. Min Act: -0.0001
Data Index: 1209468 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.3506. Min Act: -0.0001
Data Index: 525114 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.3624. Min Act: -0.0001
Data Index: 525407 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.3725. Min Act: -0.0001
Data Index: 1146927 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.0528. Min Act: -0.0001
Data Index: 1355450 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.2907. Min Act: -0.0001
Data Index: 653840 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.2219. Min Act: -0.0001
Data Index: 957220 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.3007. Min Act: -0.0001
Data Index: 859119 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.3405. Min Act: -0.0001
Data Index: 1134858 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.2864. Min Act: -0.0001
Data Index: 443120 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.2797. Min Act: -0.0001
Data Index: 100108 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.4001. Min Act: -0.0001
Data Index: 464404 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.1672. Min Act: -0.0001
Data Index: 694948 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.1747. Min Act: -0.0001
Data Index: 839826 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.0827. Min Act: -0.0001
Data Index: 512493 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.2231. Min Act: -0.0001
Data Index: 329014 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4346. Min Range: -1.4346
Max Act: 1.3132. Min Act: -0.0001
Data Index: 1343775 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19