Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3757 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.7309. Min Range: -1.7309
Max Act: 1.7033. Min Act: -0.0001
Data Index: 1203953 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7309. Min Range: -1.7309
Max Act: 1.7309. Min Act: -0.0001
Data Index: 282150 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7309. Min Range: -1.7309
Max Act: 1.4661. Min Act: -0.0001
Data Index: 1100530 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7309. Min Range: -1.7309
Max Act: 1.3773. Min Act: -0.0001
Data Index: 249917 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7309. Min Range: -1.7309
Max Act: 1.4406. Min Act: -0.0001
Data Index: 1291735 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7309. Min Range: -1.7309
Max Act: 1.2591. Min Act: -0.0001
Data Index: 1286131 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7309. Min Range: -1.7309
Max Act: 1.2553. Min Act: -0.0001
Data Index: 275716 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7309. Min Range: -1.7309
Max Act: 1.2476. Min Act: -0.0001
Data Index: 209744 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7309. Min Range: -1.7309
Max Act: 1.2369. Min Act: -0.0001
Data Index: 426342 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7309. Min Range: -1.7309
Max Act: 1.1704. Min Act: -0.0001
Data Index: 912681 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7309. Min Range: -1.7309
Max Act: 1.0003. Min Act: -0.0001
Data Index: 1166119 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7309. Min Range: -1.7309
Max Act: 0.9793. Min Act: -0.0001
Data Index: 1316091 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7309. Min Range: -1.7309
Max Act: 0.9766. Min Act: -0.0001
Data Index: 606449 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7309. Min Range: -1.7309
Max Act: 0.9733. Min Act: -0.0001
Data Index: 1079428 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7309. Min Range: -1.7309
Max Act: 0.8868. Min Act: -0.0001
Data Index: 639105 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7309. Min Range: -1.7309
Max Act: 0.8957. Min Act: -0.0001
Data Index: 1227931 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7309. Min Range: -1.7309
Max Act: 0.8760. Min Act: -0.0001
Data Index: 966406 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7309. Min Range: -1.7309
Max Act: 0.9908. Min Act: -0.0001
Data Index: 1322227 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7309. Min Range: -1.7309
Max Act: 0.9315. Min Act: -0.0001
Data Index: 65429 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7309. Min Range: -1.7309
Max Act: 0.8513. Min Act: -0.0001
Data Index: 724381 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19