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

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

Neuron 2713 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1857. Min Act: -0.0001

Data Index: 602343 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1530. Min Act: -0.0001

Data Index: 935887 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1526. Min Act: -0.0001

Data Index: 1268566 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1405. Min Act: -0.0000

Data Index: 618030 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1247453 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1082242 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1263. Min Act: -0.0000

Data Index: 907529 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1430724 (Python Code)

Max Activating Token Index: 293

Text #8

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1280. Min Act: -0.0001

Data Index: 460066 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1206. Min Act: -0.0000

Data Index: 91407 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1269. Min Act: -0.0001

Data Index: 405811 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1022666 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1268. Min Act: -0.0000

Data Index: 290443 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1209. Min Act: -0.0001

Data Index: 868291 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1258. Min Act: -0.0001

Data Index: 1050513 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1294165 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1286763 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1252. Min Act: -0.0000

Data Index: 683718 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1160. Min Act: -0.0000

Data Index: 585140 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1300. Min Act: -0.0001

Data Index: 94405 (C4 (Web Text))

Max Activating Token Index: 503