Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 283 in Layer 1
Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')
Click the toggle to see the full text!
Text #0
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.5828. Min Act: -0.0002
Data Index: 347717 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.4633. Min Act: -0.0002
Data Index: 1308519 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.3642. Min Act: -0.0002
Data Index: 858430 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.3746. Min Act: -0.0002
Data Index: 799863 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.4167. Min Act: -0.0002
Data Index: 154015 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.3905. Min Act: -0.0002
Data Index: 117979 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.3161. Min Act: -0.0002
Data Index: 13246 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.3975. Min Act: -0.0002
Data Index: 850954 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.3495. Min Act: -0.0002
Data Index: 64853 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.3333. Min Act: -0.0002
Data Index: 180383 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.3730. Min Act: -0.0002
Data Index: 1252882 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.2799. Min Act: -0.0002
Data Index: 478376 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.2766. Min Act: -0.0002
Data Index: 60977 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.3426. Min Act: -0.0002
Data Index: 642647 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.2984. Min Act: -0.0002
Data Index: 1176117 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.2395. Min Act: -0.0002
Data Index: 1295216 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.1981. Min Act: -0.0002
Data Index: 723232 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.3015. Min Act: -0.0002
Data Index: 1222225 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.2282. Min Act: -0.0002
Data Index: 976411 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 2.5828. Min Range: -2.5828
Max Act: 2.2598. Min Act: -0.0002
Data Index: 108827 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full textTruncated
Full Text #19