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

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

Neuron 3931 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1663. Min Act: -0.0000

Data Index: 143006 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1647. Min Act: -0.0001

Data Index: 534703 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1518. Min Act: -0.0000

Data Index: 407241 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1526. Min Act: -0.0000

Data Index: 361988 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1451. Min Act: -0.0000

Data Index: 576819 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1404. Min Act: -0.0000

Data Index: 956253 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1393. Min Act: -0.0000

Data Index: 710118 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1236. Min Act: -0.0000

Data Index: 281208 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1387. Min Act: -0.0000

Data Index: 31025 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1144551 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1426. Min Act: -0.0000

Data Index: 543744 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1318. Min Act: -0.0000

Data Index: 845319 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1192. Min Act: -0.0000

Data Index: 531115 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1171. Min Act: -0.0000

Data Index: 452804 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1523397 (Python Code)

Max Activating Token Index: 463

Text #15

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1243. Min Act: -0.0001

Data Index: 261864 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1151010 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1189753 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1255. Min Act: -0.0000

Data Index: 334815 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1000008 (C4 (Web Text))

Max Activating Token Index: 19