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

Dataset: The Pile

Neuron 907 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1834093 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1634. Min Act: -0.0000

Data Index: 356170 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1374967 (The Pile)

Max Activating Token Index: 641

Text #3

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1491871 (The Pile)

Max Activating Token Index: 698

Text #4

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1841091 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1444. Min Act: -0.0000

Data Index: 1771265 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1328. Min Act: -0.0000

Data Index: 838779 (The Pile)

Max Activating Token Index: 615

Text #7

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1926615 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1764096 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1366. Min Act: -0.0000

Data Index: 87915 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1349. Min Act: -0.0000

Data Index: 146924 (The Pile)

Max Activating Token Index: 460

Text #11

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1114290 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1270. Min Act: -0.0000

Data Index: 315367 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1156131 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1113975 (The Pile)

Max Activating Token Index: 562

Text #15

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1346540 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1788305 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1232. Min Act: -0.0000

Data Index: 1490419 (The Pile)

Max Activating Token Index: 942

Text #18

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1215. Min Act: -0.0000

Data Index: 96330 (The Pile)

Max Activating Token Index: 275

Text #19

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1926570 (The Pile)

Max Activating Token Index: 185