Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3276 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.9346. Min Act: -0.0001
Data Index: 555453 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.8198. Min Act: -0.0001
Data Index: 1112733 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.4742. Min Act: -0.0001
Data Index: 1003770 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.4923. Min Act: -0.0001
Data Index: 1002259 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.5035. Min Act: -0.0001
Data Index: 1154914 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.3949. Min Act: -0.0001
Data Index: 434739 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.2234. Min Act: -0.0001
Data Index: 201974 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.6459. Min Act: -0.0001
Data Index: 1009715 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.4900. Min Act: -0.0001
Data Index: 187988 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.3468. Min Act: -0.0001
Data Index: 547686 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.2611. Min Act: -0.0001
Data Index: 727478 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.2763. Min Act: -0.0001
Data Index: 679960 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.5310. Min Act: -0.0001
Data Index: 966601 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.2304. Min Act: -0.0001
Data Index: 191197 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.1265. Min Act: -0.0001
Data Index: 103462 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.1281. Min Act: -0.0001
Data Index: 568389 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9346. Min Range: -3.9346
Max Act: 2.9874. Min Act: -0.0001
Data Index: 424903 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9346. Min Range: -3.9346
Max Act: 2.9797. Min Act: -0.0001
Data Index: 416716 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.0726. Min Act: -0.0001
Data Index: 741925 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9346. Min Range: -3.9346
Max Act: 3.1787. Min Act: -0.0001
Data Index: 122578 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19