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

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

Neuron 2403 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2852. Min Act: -0.0001

Data Index: 933153 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2531. Min Act: -0.0001

Data Index: 746903 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2517. Min Act: -0.0001

Data Index: 771247 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2265. Min Act: -0.0001

Data Index: 780651 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2496. Min Act: -0.0001

Data Index: 1094092 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2483. Min Act: -0.0001

Data Index: 1135483 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2529. Min Act: -0.0001

Data Index: 1276916 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2405. Min Act: -0.0001

Data Index: 875160 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2317. Min Act: -0.0001

Data Index: 473908 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2465. Min Act: -0.0001

Data Index: 904492 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2461. Min Act: -0.0001

Data Index: 744871 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2449. Min Act: -0.0001

Data Index: 1153977 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2372. Min Act: -0.0001

Data Index: 284383 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2356. Min Act: -0.0001

Data Index: 874563 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2412. Min Act: -0.0001

Data Index: 594992 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2205. Min Act: -0.0001

Data Index: 920579 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2416. Min Act: -0.0001

Data Index: 231612 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2212. Min Act: -0.0001

Data Index: 989141 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2357. Min Act: -0.0001

Data Index: 1166427 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2260. Min Act: -0.0001

Data Index: 499140 (C4 (Web Text))

Max Activating Token Index: 537