Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3524 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.1296. Min Range: -2.1296
Max Act: 2.1296. Min Act: -0.0001
Data Index: 666664 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.9536. Min Act: -0.0001
Data Index: 955796 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.7066. Min Act: -0.0001
Data Index: 565587 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.8730. Min Act: -0.0001
Data Index: 115027 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.8456. Min Act: -0.0001
Data Index: 895581 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.7811. Min Act: -0.0001
Data Index: 36415 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.7039. Min Act: -0.0001
Data Index: 1264794 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.6160. Min Act: -0.0001
Data Index: 614285 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.6067. Min Act: -0.0001
Data Index: 591723 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.7140. Min Act: -0.0001
Data Index: 1025289 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.6016. Min Act: -0.0001
Data Index: 215744 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.5715. Min Act: -0.0001
Data Index: 823608 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.4791. Min Act: -0.0001
Data Index: 963874 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.6250. Min Act: -0.0001
Data Index: 1248724 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.5340. Min Act: -0.0001
Data Index: 396699 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.5496. Min Act: -0.0001
Data Index: 1174043 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.4522. Min Act: -0.0001
Data Index: 659497 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.5219. Min Act: -0.0001
Data Index: 812280 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.4247. Min Act: -0.0001
Data Index: 943675 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1296. Min Range: -2.1296
Max Act: 1.2844. Min Act: -0.0001
Data Index: 1030767 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19