Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2716 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.5106. Min Act: -0.0001
Data Index: 222588 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.3358. Min Act: -0.0001
Data Index: 78826 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.4113. Min Act: -0.0001
Data Index: 377877 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.4363. Min Act: -0.0001
Data Index: 621496 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.4783. Min Act: -0.0002
Data Index: 460393 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.3880. Min Act: -0.0001
Data Index: 667575 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7565. Min Range: -1.7565
Max Act: 0.9772. Min Act: -0.0001
Data Index: 797547 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.0748. Min Act: -0.0001
Data Index: 1131833 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.2992. Min Act: -0.0001
Data Index: 294409 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.2417. Min Act: -0.0001
Data Index: 1174206 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.0065. Min Act: -0.0001
Data Index: 498276 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7565. Min Range: -1.7565
Max Act: 0.8712. Min Act: -0.0001
Data Index: 983805 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.2913. Min Act: -0.0001
Data Index: 1322103 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7565. Min Range: -1.7565
Max Act: 0.8605. Min Act: -0.0001
Data Index: 967503 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7565. Min Range: -1.7565
Max Act: 0.8958. Min Act: -0.0001
Data Index: 947044 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.3281. Min Act: -0.0001
Data Index: 60610 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.7565. Min Act: -0.0001
Data Index: 601676 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7565. Min Range: -1.7565
Max Act: 0.9759. Min Act: -0.0001
Data Index: 634060 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.4406. Min Act: -0.0001
Data Index: 1240933 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7565. Min Range: -1.7565
Max Act: 1.0562. Min Act: -0.0001
Data Index: 1193077 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19