Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3097 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2806. Min Act: -0.0001

Data Index: 474329 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2789. Min Act: -0.0001

Data Index: 702709 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2464. Min Act: -0.0001

Data Index: 634876 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2593. Min Act: -0.0001

Data Index: 389972 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2507. Min Act: -0.0001

Data Index: 1343121 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2401. Min Act: -0.0001

Data Index: 603198 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2392. Min Act: -0.0001

Data Index: 266252 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2431. Min Act: -0.0001

Data Index: 1076122 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2444. Min Act: -0.0001

Data Index: 728823 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2365. Min Act: -0.0001

Data Index: 650547 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2202. Min Act: -0.0001

Data Index: 243195 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2347. Min Act: -0.0001

Data Index: 938701 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2175. Min Act: -0.0001

Data Index: 475980 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2396. Min Act: -0.0001

Data Index: 605396 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2257. Min Act: -0.0001

Data Index: 89681 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2370. Min Act: -0.0001

Data Index: 89884 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2187. Min Act: -0.0001

Data Index: 58745 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2282. Min Act: -0.0001

Data Index: 635691 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2292. Min Act: -0.0001

Data Index: 496813 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2350. Min Act: -0.0001

Data Index: 472662 (C4 (Web Text))

Max Activating Token Index: 928