Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 775 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.2763. Min Range: -1.2763
Max Act: 1.2763. Min Act: -0.0001
Data Index: 2668 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2763. Min Range: -1.2763
Max Act: 1.1053. Min Act: -0.0001
Data Index: 835841 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2763. Min Range: -1.2763
Max Act: 1.0745. Min Act: -0.0001
Data Index: 975717 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2763. Min Range: -1.2763
Max Act: 1.0432. Min Act: -0.0001
Data Index: 420506 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.9585. Min Act: -0.0001
Data Index: 1063856 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.9149. Min Act: -0.0001
Data Index: 280887 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.9107. Min Act: -0.0001
Data Index: 776594 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.9341. Min Act: -0.0001
Data Index: 1118673 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2763. Min Range: -1.2763
Max Act: 1.0291. Min Act: -0.0001
Data Index: 1033260 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.9241. Min Act: -0.0001
Data Index: 522782 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.8687. Min Act: -0.0001
Data Index: 619827 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.8692. Min Act: -0.0001
Data Index: 907924 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.8633. Min Act: -0.0001
Data Index: 712609 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.8613. Min Act: -0.0001
Data Index: 441020 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.8324. Min Act: -0.0001
Data Index: 1021997 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.8527. Min Act: -0.0001
Data Index: 846450 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.8946. Min Act: -0.0001
Data Index: 331084 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.8918. Min Act: -0.0001
Data Index: 504280 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.8422. Min Act: -0.0001
Data Index: 826065 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2763. Min Range: -1.2763
Max Act: 0.8655. Min Act: -0.0001
Data Index: 1134332 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19