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

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

Neuron 968 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1671. Min Act: -0.0001

Data Index: 177656 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1601. Min Act: -0.0001

Data Index: 361503 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1516. Min Act: -0.0001

Data Index: 1405659 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1531. Min Act: -0.0001

Data Index: 326258 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1311. Min Act: -0.0001

Data Index: 513225 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1495. Min Act: -0.0001

Data Index: 393232 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1450. Min Act: -0.0001

Data Index: 466977 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1351. Min Act: -0.0001

Data Index: 1566416 (Python Code)

Max Activating Token Index: 893

Text #8

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1278. Min Act: -0.0001

Data Index: 145781 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1261000 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1300. Min Act: -0.0001

Data Index: 739018 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1298. Min Act: -0.0001

Data Index: 485241 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1175372 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1304. Min Act: -0.0001

Data Index: 636306 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1133218 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1175. Min Act: -0.0001

Data Index: 803946 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1236. Min Act: -0.0001

Data Index: 412239 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1572859 (Python Code)

Max Activating Token Index: 158

Text #18

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1106665 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1164. Min Act: -0.0001

Data Index: 302219 (C4 (Web Text))

Max Activating Token Index: 118