Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3929 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.4193. Min Act: -0.0000

Data Index: 1511650 (Python Code)

Max Activating Token Index: 240

Text #1

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.3111. Min Act: -0.0000

Data Index: 256155 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.2912. Min Act: -0.0000

Data Index: 1527809 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1580377 (Python Code)

Max Activating Token Index: 723

Text #4

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1343. Min Act: -0.0000

Data Index: 962840 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1967. Min Act: -0.0000

Data Index: 655225 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.2443. Min Act: -0.0000

Data Index: 1183943 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1534378 (Python Code)

Max Activating Token Index: 460

Text #8

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1854. Min Act: -0.0000

Data Index: 416399 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1099. Min Act: -0.0000

Data Index: 266144 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1512559 (Python Code)

Max Activating Token Index: 277

Text #11

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1214. Min Act: -0.0000

Data Index: 1578303 (Python Code)

Max Activating Token Index: 760

Text #12

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.0289. Min Act: -0.0000

Data Index: 816993 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1564. Min Act: -0.0000

Data Index: 257874 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.0727. Min Act: -0.0000

Data Index: 581305 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1304. Min Act: -0.0000

Data Index: 1285329 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.1298. Min Act: -0.0000

Data Index: 1005633 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 1.4193. Min Range: -1.4193

Max Act: 0.9629. Min Act: -0.0000

Data Index: 188557 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1274889 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 1.4193. Min Range: -1.4193

Max Act: 1.0158. Min Act: -0.0000

Data Index: 1213630 (C4 (Web Text))

Max Activating Token Index: 968