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

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

Neuron 2515 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1750. Min Range: -1.1750

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1354608 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 1.1750. Min Range: -1.1750

Max Act: 1.0152. Min Act: -0.0000

Data Index: 528749 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.1750. Min Range: -1.1750

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1165145 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 1.1750. Min Range: -1.1750

Max Act: 1.0283. Min Act: -0.0000

Data Index: 1232624 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 1.1750. Min Range: -1.1750

Max Act: 1.0285. Min Act: -0.0000

Data Index: 281086 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 1.1750. Min Range: -1.1750

Max Act: 1.1358. Min Act: -0.0000

Data Index: 928491 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.9623. Min Act: -0.0000

Data Index: 995276 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.9565. Min Act: -0.0000

Data Index: 382004 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.9385. Min Act: -0.0000

Data Index: 199507 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.9244. Min Act: -0.0000

Data Index: 467359 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1108359 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1039526 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.9078. Min Act: -0.0000

Data Index: 674270 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8886. Min Act: -0.0000

Data Index: 305293 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.9570. Min Act: -0.0000

Data Index: 107294 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8393. Min Act: -0.0000

Data Index: 674178 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.9622. Min Act: -0.0000

Data Index: 94177 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8726. Min Act: -0.0000

Data Index: 872456 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 1.1750. Min Range: -1.1750

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1046084 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 1.1750. Min Range: -1.1750

Max Act: 1.0406. Min Act: -0.0000

Data Index: 1354118 (C4 (Web Text))

Max Activating Token Index: 288