Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4035 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.7760. Min Act: -0.0001
Data Index: 347884 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.8323. Min Act: -0.0001
Data Index: 274622 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.9395. Min Act: -0.0001
Data Index: 888782 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.6313. Min Act: -0.0001
Data Index: 942244 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.6283. Min Act: -0.0001
Data Index: 769723 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.5194. Min Act: -0.0001
Data Index: 1188979 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.5633. Min Act: -0.0001
Data Index: 643857 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.4972. Min Act: -0.0001
Data Index: 6721 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.5539. Min Act: -0.0001
Data Index: 141082 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.5421. Min Act: -0.0001
Data Index: 1214751 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.5515. Min Act: -0.0001
Data Index: 874370 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.4887. Min Act: -0.0001
Data Index: 272064 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.4929. Min Act: -0.0001
Data Index: 529917 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.4362. Min Act: -0.0001
Data Index: 965869 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.3977. Min Act: -0.0001
Data Index: 1154428 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.4398. Min Act: -0.0001
Data Index: 232914 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.3897. Min Act: -0.0001
Data Index: 211695 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.3549. Min Act: -0.0001
Data Index: 1106161 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.5380. Min Act: -0.0001
Data Index: 1050146 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9395. Min Range: -1.9395
Max Act: 1.4201. Min Act: -0.0001
Data Index: 1289289 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19