Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5460 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3781. Min Act: -0.0001

Data Index: 878979 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3053. Min Act: -0.0001

Data Index: 1142116 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3174. Min Act: -0.0001

Data Index: 149067 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2848. Min Act: -0.0001

Data Index: 308940 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2853. Min Act: -0.0001

Data Index: 599026 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2808. Min Act: -0.0001

Data Index: 1344423 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2577. Min Act: -0.0001

Data Index: 50240 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2772. Min Act: -0.0001

Data Index: 584402 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2794. Min Act: -0.0001

Data Index: 81737 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2615. Min Act: -0.0001

Data Index: 266284 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2606. Min Act: -0.0001

Data Index: 1108671 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2440. Min Act: -0.0001

Data Index: 529495 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2540. Min Act: -0.0001

Data Index: 145458 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2680. Min Act: -0.0001

Data Index: 667370 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2640. Min Act: -0.0001

Data Index: 320975 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2559. Min Act: -0.0001

Data Index: 735494 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2434. Min Act: -0.0001

Data Index: 1283052 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2432. Min Act: -0.0001

Data Index: 870860 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2339. Min Act: -0.0001

Data Index: 825407 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2415. Min Act: -0.0001

Data Index: 839066 (C4 (Web Text))

Max Activating Token Index: 17