Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3448 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6924. Min Range: -2.6924
Max Act: 2.6924. Min Act: -0.0001
Data Index: 996626 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6924. Min Range: -2.6924
Max Act: 2.3065. Min Act: -0.0001
Data Index: 475611 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6924. Min Range: -2.6924
Max Act: 2.4664. Min Act: -0.0001
Data Index: 283896 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6924. Min Range: -2.6924
Max Act: 2.1624. Min Act: -0.0001
Data Index: 55600 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6924. Min Range: -2.6924
Max Act: 2.0349. Min Act: -0.0001
Data Index: 703281 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6924. Min Range: -2.6924
Max Act: 2.1308. Min Act: -0.0001
Data Index: 851768 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6924. Min Range: -2.6924
Max Act: 2.2214. Min Act: -0.0001
Data Index: 194436 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6924. Min Range: -2.6924
Max Act: 2.1861. Min Act: -0.0001
Data Index: 174655 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6924. Min Range: -2.6924
Max Act: 1.7987. Min Act: -0.0001
Data Index: 1186406 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6924. Min Range: -2.6924
Max Act: 1.9995. Min Act: -0.0001
Data Index: 507752 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6924. Min Range: -2.6924
Max Act: 1.9566. Min Act: -0.0001
Data Index: 435924 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6924. Min Range: -2.6924
Max Act: 1.7380. Min Act: -0.0001
Data Index: 1010211 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6924. Min Range: -2.6924
Max Act: 1.7386. Min Act: -0.0001
Data Index: 1005753 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6924. Min Range: -2.6924
Max Act: 2.0205. Min Act: -0.0000
Data Index: 1216955 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6924. Min Range: -2.6924
Max Act: 1.7970. Min Act: -0.0001
Data Index: 96138 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6924. Min Range: -2.6924
Max Act: 1.6709. Min Act: -0.0001
Data Index: 949033 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6924. Min Range: -2.6924
Max Act: 1.8402. Min Act: -0.0001
Data Index: 719224 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6924. Min Range: -2.6924
Max Act: 1.6021. Min Act: -0.0000
Data Index: 171633 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6924. Min Range: -2.6924
Max Act: 1.6716. Min Act: -0.0001
Data Index: 542530 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6924. Min Range: -2.6924
Max Act: 1.7445. Min Act: -0.0001
Data Index: 961195 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19