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

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

Neuron 3316 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: 0.1627. Min Range: -0.1627

Max Act: 0.1627. Min Act: -0.0001

Data Index: 679388 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1466. Min Act: -0.0001

Data Index: 899180 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1396. Min Act: -0.0001

Data Index: 995428 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1451. Min Act: -0.0001

Data Index: 364380 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1392. Min Act: -0.0001

Data Index: 182878 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1388. Min Act: -0.0001

Data Index: 660030 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1338. Min Act: -0.0001

Data Index: 485210 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1163676 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1287. Min Act: -0.0001

Data Index: 309296 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1171793 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1315. Min Act: -0.0001

Data Index: 451765 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1330. Min Act: -0.0001

Data Index: 597928 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1256. Min Act: -0.0001

Data Index: 990964 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1286. Min Act: -0.0001

Data Index: 718192 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1060. Min Act: -0.0001

Data Index: 728140 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1217. Min Act: -0.0001

Data Index: 480792 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1163. Min Act: -0.0001

Data Index: 986218 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1235. Min Act: -0.0001

Data Index: 990820 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1023648 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.1627. Min Range: -0.1627

Max Act: 0.1214. Min Act: -0.0001

Data Index: 404546 (C4 (Web Text))

Max Activating Token Index: 715