Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2972 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 6.2421. Min Range: -6.2421
Max Act: 6.2421. Min Act: -0.0001
Data Index: 1154633 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.5798. Min Act: -0.0001
Data Index: 500677 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.5682. Min Act: -0.0001
Data Index: 27799 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.7312. Min Act: -0.0001
Data Index: 933215 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.5378. Min Act: -0.0001
Data Index: 1312171 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.1316. Min Act: -0.0001
Data Index: 148348 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.6880. Min Act: -0.0001
Data Index: 650390 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.4837. Min Act: -0.0001
Data Index: 1268975 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.2921. Min Act: -0.0001
Data Index: 96656 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.2456. Min Act: -0.0001
Data Index: 419945 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.1880. Min Act: -0.0001
Data Index: 35312 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2421. Min Range: -6.2421
Max Act: 4.9967. Min Act: -0.0001
Data Index: 512980 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.1500. Min Act: -0.0001
Data Index: 798244 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.2881. Min Act: -0.0001
Data Index: 522483 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.0806. Min Act: -0.0001
Data Index: 543149 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.0878. Min Act: -0.0001
Data Index: 850709 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2421. Min Range: -6.2421
Max Act: 4.8362. Min Act: -0.0001
Data Index: 361020 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2421. Min Range: -6.2421
Max Act: 5.4778. Min Act: -0.0001
Data Index: 754776 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2421. Min Range: -6.2421
Max Act: 4.7534. Min Act: -0.0001
Data Index: 736209 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2421. Min Range: -6.2421
Max Act: 4.8770. Min Act: -0.0001
Data Index: 666947 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19