Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3285 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.2153. Min Act: -0.0000

Data Index: 311354 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1446663 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.9304. Min Act: 0.0000

Data Index: 1422139 (The Pile)

Max Activating Token Index: 902

Text #3

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.9289. Min Act: -0.0000

Data Index: 463322 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.9589. Min Act: -0.0000

Data Index: 386931 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.8509. Min Act: -0.0000

Data Index: 917225 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.8623. Min Act: 0.0000

Data Index: 1802996 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1484226 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.8751. Min Act: 0.0000

Data Index: 119234 (The Pile)

Max Activating Token Index: 498

Text #9

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.8526. Min Act: 0.0000

Data Index: 822791 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1012476 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1962705 (The Pile)

Max Activating Token Index: 643

Text #12

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.7873. Min Act: -0.0000

Data Index: 1323402 (The Pile)

Max Activating Token Index: 732

Text #13

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.8375. Min Act: -0.0000

Data Index: 209631 (The Pile)

Max Activating Token Index: 410

Text #14

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.7979. Min Act: -0.0000

Data Index: 335205 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.7836. Min Act: -0.0000

Data Index: 621881 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.7921. Min Act: -0.0000

Data Index: 251282 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1237521 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1635969 (The Pile)

Max Activating Token Index: 920

Text #19

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1027856 (The Pile)

Max Activating Token Index: 526