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

Dataset: The Pile

Neuron 1894 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.3081. Min Act: -0.0000

Data Index: 96246 (The Pile)

Max Activating Token Index: 184

Text #1

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1904174 (The Pile)

Max Activating Token Index: 403

Text #2

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1049933 (The Pile)

Max Activating Token Index: 369

Text #3

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2346. Min Act: -0.0000

Data Index: 157079 (The Pile)

Max Activating Token Index: 252

Text #4

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2206. Min Act: -0.0000

Data Index: 417466 (The Pile)

Max Activating Token Index: 211

Text #5

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1952473 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1000274 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2452. Min Act: -0.0000

Data Index: 602636 (The Pile)

Max Activating Token Index: 855

Text #8

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2356. Min Act: -0.0000

Data Index: 194424 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1665516 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1266207 (The Pile)

Max Activating Token Index: 119

Text #11

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2110. Min Act: -0.0000

Data Index: 490658 (The Pile)

Max Activating Token Index: 448

Text #12

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2363. Min Act: -0.0000

Data Index: 53110 (The Pile)

Max Activating Token Index: 570

Text #13

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2207. Min Act: -0.0000

Data Index: 401073 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1376181 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1940514 (The Pile)

Max Activating Token Index: 523

Text #16

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1399262 (The Pile)

Max Activating Token Index: 31

Text #17

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1953. Min Act: -0.0000

Data Index: 338032 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2069. Min Act: -0.0000

Data Index: 607102 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1745141 (The Pile)

Max Activating Token Index: 37