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

Dataset: The Pile

Neuron 996 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.5242. Min Act: -0.0000

Data Index: 547328 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3544. Min Act: -0.0000

Data Index: 679712 (The Pile)

Max Activating Token Index: 226

Text #2

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1951. Min Act: -0.0000

Data Index: 182707 (The Pile)

Max Activating Token Index: 897

Text #3

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1822. Min Act: -0.0000

Data Index: 91100 (The Pile)

Max Activating Token Index: 792

Text #4

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2126. Min Act: -0.0000

Data Index: 938833 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3459. Min Act: -0.0000

Data Index: 1211521 (The Pile)

Max Activating Token Index: 65

Text #6

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2913. Min Act: -0.0000

Data Index: 1188058 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2667. Min Act: -0.0000

Data Index: 925142 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2136. Min Act: -0.0000

Data Index: 1223173 (The Pile)

Max Activating Token Index: 727

Text #9

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2172. Min Act: -0.0000

Data Index: 1577732 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2435. Min Act: -0.0000

Data Index: 1211096 (The Pile)

Max Activating Token Index: 152

Text #11

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2396. Min Act: -0.0000

Data Index: 719944 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2611. Min Act: -0.0000

Data Index: 293387 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3182. Min Act: -0.0000

Data Index: 1781076 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1799. Min Act: -0.0000

Data Index: 1469095 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1590. Min Act: -0.0000

Data Index: 693712 (The Pile)

Max Activating Token Index: 872

Text #16

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1775. Min Act: -0.0000

Data Index: 834784 (The Pile)

Max Activating Token Index: 318

Text #17

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1713. Min Act: -0.0000

Data Index: 809714 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1335. Min Act: -0.0000

Data Index: 1867198 (The Pile)

Max Activating Token Index: 201

Text #19

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1402704 (The Pile)

Max Activating Token Index: 610