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

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

Neuron 5415 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.6281. Min Act: -0.0001

Data Index: 195879 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.5936. Min Act: -0.0000

Data Index: 34607 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.5602. Min Act: -0.0001

Data Index: 715721 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.5131. Min Act: -0.0001

Data Index: 431089 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.4757. Min Act: -0.0000

Data Index: 1353305 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.4888. Min Act: -0.0000

Data Index: 980468 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.5378. Min Act: -0.0000

Data Index: 78612 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.4819. Min Act: -0.0000

Data Index: 1000449 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.4178. Min Act: -0.0000

Data Index: 58711 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.4157. Min Act: -0.0000

Data Index: 612409 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.3759. Min Act: -0.0001

Data Index: 776171 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.3242. Min Act: -0.0000

Data Index: 1313752 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.4341. Min Act: -0.0001

Data Index: 469208 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.3358. Min Act: -0.0001

Data Index: 842208 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.2365. Min Act: -0.0001

Data Index: 772496 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.3867. Min Act: -0.0001

Data Index: 374220 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.2812. Min Act: -0.0001

Data Index: 846335 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.2460. Min Act: -0.0000

Data Index: 1093834 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.2734. Min Act: -0.0000

Data Index: 729518 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.2408. Min Act: -0.0001

Data Index: 507929 (C4 (Web Text))

Max Activating Token Index: 382