Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2040 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.6425. Min Act: -0.0001
Data Index: 1025219 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.5877. Min Act: -0.0001
Data Index: 254187 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.5721. Min Act: -0.0001
Data Index: 590506 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.5321. Min Act: -0.0001
Data Index: 968511 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.5138. Min Act: -0.0001
Data Index: 627444 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.4625. Min Act: -0.0001
Data Index: 1110426 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.3133. Min Act: -0.0001
Data Index: 731874 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.2241. Min Act: -0.0001
Data Index: 1040055 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.1042. Min Act: -0.0001
Data Index: 699581 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.2320. Min Act: -0.0001
Data Index: 57344 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.2855. Min Act: -0.0001
Data Index: 403738 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.1915. Min Act: -0.0001
Data Index: 413598 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.2425. Min Act: -0.0001
Data Index: 1285921 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.1985. Min Act: -0.0001
Data Index: 1355165 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.0829. Min Act: -0.0001
Data Index: 699416 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.2272. Min Act: -0.0001
Data Index: 183651 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.1128. Min Act: -0.0001
Data Index: 736358 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.1155. Min Act: -0.0001
Data Index: 563998 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.1095. Min Act: -0.0001
Data Index: 403183 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6425. Min Range: -1.6425
Max Act: 1.0766. Min Act: -0.0001
Data Index: 666271 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19