Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3553 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.2294. Min Range: -3.2294
Max Act: 3.2294. Min Act: -0.0001
Data Index: 1212801 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2294. Min Range: -3.2294
Max Act: 3.0105. Min Act: -0.0001
Data Index: 152608 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.5283. Min Act: -0.0001
Data Index: 416547 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.2691. Min Act: -0.0001
Data Index: 152634 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.4857. Min Act: -0.0001
Data Index: 1061951 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.2281. Min Act: -0.0001
Data Index: 1316719 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.1436. Min Act: -0.0001
Data Index: 661034 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.3219. Min Act: -0.0001
Data Index: 748245 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.2502. Min Act: -0.0001
Data Index: 1032714 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.2331. Min Act: -0.0001
Data Index: 319752 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.2113. Min Act: -0.0001
Data Index: 81000 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.0869. Min Act: -0.0001
Data Index: 987066 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.0684. Min Act: -0.0001
Data Index: 357351 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.0413. Min Act: -0.0001
Data Index: 1261332 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.0106. Min Act: -0.0001
Data Index: 1116353 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2294. Min Range: -3.2294
Max Act: 1.9928. Min Act: -0.0001
Data Index: 795182 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2294. Min Range: -3.2294
Max Act: 1.9702. Min Act: -0.0001
Data Index: 1174655 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.0757. Min Act: -0.0001
Data Index: 1230743 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.1731. Min Act: -0.0001
Data Index: 829659 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2294. Min Range: -3.2294
Max Act: 2.0537. Min Act: -0.0001
Data Index: 273428 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19