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

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

Neuron 1748 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: 0.2216. Min Range: -0.2216

Max Act: 0.2216. Min Act: -0.0001

Data Index: 664151 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1890. Min Act: -0.0001

Data Index: 142825 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1693. Min Act: -0.0001

Data Index: 319337 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1610. Min Act: -0.0000

Data Index: 149102 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1699. Min Act: -0.0000

Data Index: 838177 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1188210 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1256397 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1581. Min Act: -0.0001

Data Index: 846409 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1306900 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1472. Min Act: -0.0000

Data Index: 733526 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1322476 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1412. Min Act: -0.0000

Data Index: 287695 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1495. Min Act: -0.0000

Data Index: 451714 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1419. Min Act: -0.0000

Data Index: 83852 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1514. Min Act: -0.0001

Data Index: 657020 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1365. Min Act: -0.0001

Data Index: 1646018 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1295. Min Act: -0.0001

Data Index: 1341876 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1419. Min Act: -0.0000

Data Index: 918813 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1016949 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1402. Min Act: -0.0001

Data Index: 1227397 (C4 (Web Text))

Max Activating Token Index: 173