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

Dataset: The Pile

Neuron 2357 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.5470. Min Act: -0.0000

Data Index: 548357 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.6265. Min Act: -0.0000

Data Index: 630402 (The Pile)

Max Activating Token Index: 182

Text #2

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.3602. Min Act: -0.0000

Data Index: 1242711 (The Pile)

Max Activating Token Index: 490

Text #3

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.3117. Min Act: -0.0000

Data Index: 1315748 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1018231 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.1702. Min Act: -0.0000

Data Index: 539809 (The Pile)

Max Activating Token Index: 897

Text #6

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.0969. Min Act: -0.0000

Data Index: 1938280 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.0761. Min Act: -0.0000

Data Index: 1832256 (The Pile)

Max Activating Token Index: 310

Text #8

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.0164. Min Act: -0.0000

Data Index: 218734 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.0819. Min Act: -0.0000

Data Index: 684776 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.0064. Min Act: -0.0000

Data Index: 1717601 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.1305. Min Act: -0.0000

Data Index: 835351 (The Pile)

Max Activating Token Index: 742

Text #12

Max Range: 1.6265. Min Range: -1.6265

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1462879 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.0377. Min Act: -0.0000

Data Index: 104635 (The Pile)

Max Activating Token Index: 230

Text #14

Max Range: 1.6265. Min Range: -1.6265

Max Act: 0.9975. Min Act: -0.0000

Data Index: 675742 (The Pile)

Max Activating Token Index: 11

Text #15

Max Range: 1.6265. Min Range: -1.6265

Max Act: 0.9879. Min Act: -0.0000

Data Index: 1673893 (The Pile)

Max Activating Token Index: 198

Text #16

Max Range: 1.6265. Min Range: -1.6265

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1428619 (The Pile)

Max Activating Token Index: 161

Text #17

Max Range: 1.6265. Min Range: -1.6265

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1971454 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 1.6265. Min Range: -1.6265

Max Act: 0.9105. Min Act: -0.0000

Data Index: 739476 (The Pile)

Max Activating Token Index: 990

Text #19

Max Range: 1.6265. Min Range: -1.6265

Max Act: 0.9407. Min Act: -0.0000

Data Index: 6798 (The Pile)

Max Activating Token Index: 140