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

Dataset: The Pile

Neuron 1064 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1476. Min Range: -1.1476

Max Act: 1.1476. Min Act: -0.0000

Data Index: 179266 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.9709. Min Act: -0.0000

Data Index: 774143 (The Pile)

Max Activating Token Index: 248

Text #2

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.9236. Min Act: -0.0000

Data Index: 254354 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.9205. Min Act: -0.0000

Data Index: 796284 (The Pile)

Max Activating Token Index: 393

Text #4

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1243210 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.8253. Min Act: -0.0000

Data Index: 695199 (The Pile)

Max Activating Token Index: 32

Text #6

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.7970. Min Act: -0.0000

Data Index: 829026 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1083989 (The Pile)

Max Activating Token Index: 973

Text #8

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1425668 (The Pile)

Max Activating Token Index: 967

Text #9

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1776717 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.7053. Min Act: -0.0000

Data Index: 743991 (The Pile)

Max Activating Token Index: 350

Text #11

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.7427. Min Act: -0.0000

Data Index: 729974 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1916899 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.7193. Min Act: -0.0000

Data Index: 160814 (The Pile)

Max Activating Token Index: 193

Text #14

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.6795. Min Act: -0.0000

Data Index: 816973 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.6710. Min Act: -0.0000

Data Index: 777917 (The Pile)

Max Activating Token Index: 90

Text #16

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.6851. Min Act: -0.0000

Data Index: 379994 (The Pile)

Max Activating Token Index: 954

Text #17

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.7109. Min Act: -0.0000

Data Index: 880289 (The Pile)

Max Activating Token Index: 156

Text #18

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1334019 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 1.1476. Min Range: -1.1476

Max Act: 0.7907. Min Act: -0.0000

Data Index: 163906 (The Pile)

Max Activating Token Index: 208