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

Dataset: The Pile

Neuron 615 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: 1.4178. Min Range: -1.4178

Max Act: 1.4178. Min Act: -0.0000

Data Index: 693189 (The Pile)

Max Activating Token Index: 392

Text #1

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2124. Min Act: -0.0000

Data Index: 1921584 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2366. Min Act: -0.0000

Data Index: 938429 (The Pile)

Max Activating Token Index: 341

Text #3

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1517. Min Act: -0.0000

Data Index: 164275 (The Pile)

Max Activating Token Index: 634

Text #4

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2413. Min Act: -0.0000

Data Index: 1061942 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0940. Min Act: -0.0000

Data Index: 612580 (The Pile)

Max Activating Token Index: 797

Text #6

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1056. Min Act: -0.0000

Data Index: 655550 (The Pile)

Max Activating Token Index: 264

Text #7

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0608. Min Act: -0.0000

Data Index: 367735 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1167. Min Act: -0.0000

Data Index: 857770 (The Pile)

Max Activating Token Index: 267

Text #9

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0451. Min Act: -0.0000

Data Index: 1549463 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1379241 (The Pile)

Max Activating Token Index: 947

Text #11

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0218. Min Act: -0.0000

Data Index: 43113 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.9640. Min Act: -0.0000

Data Index: 296227 (The Pile)

Max Activating Token Index: 686

Text #13

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0466. Min Act: -0.0000

Data Index: 507821 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0213. Min Act: -0.0000

Data Index: 1493282 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0464. Min Act: -0.0000

Data Index: 144710 (The Pile)

Max Activating Token Index: 185

Text #16

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0498. Min Act: -0.0000

Data Index: 34585 (The Pile)

Max Activating Token Index: 48

Text #17

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0687. Min Act: -0.0000

Data Index: 1090379 (The Pile)

Max Activating Token Index: 503

Text #18

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1227021 (The Pile)

Max Activating Token Index: 645

Text #19

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1894950 (The Pile)

Max Activating Token Index: 362