Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4490 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.3319. Min Range: -3.3319
Max Act: 3.3319. Min Act: -0.0001
Data Index: 1004654 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3319. Min Range: -3.3319
Max Act: 3.2808. Min Act: -0.0001
Data Index: 795183 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.9712. Min Act: -0.0001
Data Index: 1099663 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3319. Min Range: -3.3319
Max Act: 3.0759. Min Act: -0.0001
Data Index: 308907 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3319. Min Range: -3.3319
Max Act: 3.0832. Min Act: -0.0001
Data Index: 65885 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3319. Min Range: -3.3319
Max Act: 3.1662. Min Act: -0.0001
Data Index: 945585 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.9928. Min Act: -0.0001
Data Index: 1154431 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.8449. Min Act: -0.0001
Data Index: 1118480 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.8227. Min Act: -0.0001
Data Index: 998741 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.8149. Min Act: -0.0001
Data Index: 987945 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.8263. Min Act: -0.0001
Data Index: 637787 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.9271. Min Act: -0.0001
Data Index: 347160 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.8530. Min Act: -0.0001
Data Index: 920935 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.8797. Min Act: -0.0001
Data Index: 915893 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.9925. Min Act: -0.0001
Data Index: 871327 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.8421. Min Act: -0.0001
Data Index: 246835 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.8302. Min Act: -0.0001
Data Index: 1345294 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.8145. Min Act: -0.0001
Data Index: 1068157 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.8129. Min Act: -0.0001
Data Index: 1150727 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3319. Min Range: -3.3319
Max Act: 2.8037. Min Act: -0.0001
Data Index: 300861 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19