Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4360 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1329132 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3773. Min Act: -0.0000

Data Index: 427092 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3385. Min Act: -0.0000

Data Index: 884351 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3396. Min Act: -0.0000

Data Index: 431854 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1327598 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1237417 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3071. Min Act: -0.0000

Data Index: 552162 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3184. Min Act: -0.0000

Data Index: 374242 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2908. Min Act: -0.0000

Data Index: 341837 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3241. Min Act: -0.0000

Data Index: 833782 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2986. Min Act: -0.0000

Data Index: 275636 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.3153. Min Act: -0.0000

Data Index: 741548 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2914. Min Act: -0.0000

Data Index: 552169 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2919. Min Act: -0.0000

Data Index: 603129 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2707. Min Act: -0.0000

Data Index: 1239437 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2827. Min Act: -0.0000

Data Index: 811841 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2714. Min Act: -0.0000

Data Index: 581483 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2821. Min Act: -0.0000

Data Index: 178305 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2739. Min Act: -0.0000

Data Index: 833897 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.3773. Min Range: -0.3773

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1248409 (C4 (Web Text))

Max Activating Token Index: 393