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

Dataset: The Pile

Neuron 3372 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: 0.4243. Min Range: -0.4243

Max Act: 0.4243. Min Act: -0.0000

Data Index: 464936 (The Pile)

Max Activating Token Index: 11

Text #1

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3860. Min Act: -0.0000

Data Index: 149203 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1287276 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1293764 (The Pile)

Max Activating Token Index: 191

Text #4

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3312. Min Act: -0.0000

Data Index: 501952 (The Pile)

Max Activating Token Index: 744

Text #5

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3402. Min Act: -0.0000

Data Index: 353280 (The Pile)

Max Activating Token Index: 297

Text #6

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3423. Min Act: -0.0000

Data Index: 361910 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3271. Min Act: -0.0000

Data Index: 568070 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1385586 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3232. Min Act: -0.0000

Data Index: 159122 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3277. Min Act: -0.0000

Data Index: 1831612 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.2969. Min Act: -0.0000

Data Index: 889003 (The Pile)

Max Activating Token Index: 1008

Text #12

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3007. Min Act: -0.0000

Data Index: 240129 (The Pile)

Max Activating Token Index: 871

Text #13

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1764025 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1266613 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1910509 (The Pile)

Max Activating Token Index: 709

Text #16

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.2934. Min Act: -0.0000

Data Index: 351997 (The Pile)

Max Activating Token Index: 471

Text #17

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1214468 (The Pile)

Max Activating Token Index: 627

Text #18

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1193808 (The Pile)

Max Activating Token Index: 11

Text #19

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3064. Min Act: -0.0000

Data Index: 989835 (The Pile)

Max Activating Token Index: 14