Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 314 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1483. Min Act: -0.0000

Data Index: 999743 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1214317 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1378. Min Act: -0.0001

Data Index: 251337 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1366. Min Act: -0.0000

Data Index: 1345104 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1132101 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1285. Min Act: -0.0001

Data Index: 58624 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1347. Min Act: 0.0001

Data Index: 700940 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1294. Min Act: -0.0001

Data Index: 379955 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1095020 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1280. Min Act: -0.0000

Data Index: 848394 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1328. Min Act: 0.0000

Data Index: 1275394 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1182257 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1216. Min Act: -0.0001

Data Index: 212187 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1211. Min Act: -0.0001

Data Index: 13362 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1220. Min Act: -0.0001

Data Index: 738849 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1212. Min Act: -0.0000

Data Index: 363921 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1195. Min Act: -0.0001

Data Index: 491296 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1182. Min Act: -0.0001

Data Index: 1046281 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1143. Min Act: -0.0001

Data Index: 673528 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1167. Min Act: -0.0001

Data Index: 136920 (C4 (Web Text))

Max Activating Token Index: 206