Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 954 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.6088. Min Act: -0.0001
Data Index: 47088 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.6108. Min Act: -0.0001
Data Index: 44074 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.5188. Min Act: -0.0001
Data Index: 795528 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.4468. Min Act: -0.0001
Data Index: 566740 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.5770. Min Act: -0.0001
Data Index: 33368 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.4383. Min Act: -0.0001
Data Index: 39968 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.2835. Min Act: -0.0001
Data Index: 883090 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.1339. Min Act: -0.0001
Data Index: 723933 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.3699. Min Act: -0.0001
Data Index: 1100865 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.2417. Min Act: -0.0001
Data Index: 1226631 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.4550. Min Act: -0.0001
Data Index: 1134144 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.2172. Min Act: -0.0001
Data Index: 1213942 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.1449. Min Act: -0.0001
Data Index: 725692 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.3789. Min Act: -0.0001
Data Index: 1009514 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.1266. Min Act: -0.0001
Data Index: 810192 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.1858. Min Act: -0.0001
Data Index: 1027834 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.2250. Min Act: -0.0001
Data Index: 985888 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.1513. Min Act: -0.0001
Data Index: 619468 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.1007. Min Act: -0.0001
Data Index: 513397 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6108. Min Range: -2.6108
Max Act: 2.2697. Min Act: -0.0001
Data Index: 755357 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19