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

Dataset: The Pile

Neuron 966 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: 4.2959. Min Range: -4.2959

Max Act: 4.2959. Min Act: -0.0000

Data Index: 1060046 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.7274. Min Act: -0.0000

Data Index: 536572 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9948. Min Act: -0.0000

Data Index: 1202420 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.8760. Min Act: -0.0000

Data Index: 1068061 (The Pile)

Max Activating Token Index: 230

Text #4

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.6925. Min Act: -0.0000

Data Index: 177167 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.7397. Min Act: -0.0000

Data Index: 1709055 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.8311. Min Act: -0.0000

Data Index: 413790 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9792. Min Act: -0.0000

Data Index: 511211 (The Pile)

Max Activating Token Index: 159

Text #8

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9947. Min Act: -0.0000

Data Index: 959054 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.8311. Min Act: -0.0000

Data Index: 1968965 (The Pile)

Max Activating Token Index: 215

Text #10

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9335. Min Act: -0.0000

Data Index: 277856 (The Pile)

Max Activating Token Index: 263

Text #11

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.1169. Min Act: -0.0000

Data Index: 537962 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.7595. Min Act: -0.0000

Data Index: 1713541 (The Pile)

Max Activating Token Index: 743

Text #13

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9159. Min Act: -0.0000

Data Index: 641818 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9198. Min Act: -0.0000

Data Index: 209828 (The Pile)

Max Activating Token Index: 116

Text #15

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.2460. Min Act: -0.0000

Data Index: 206399 (The Pile)

Max Activating Token Index: 71

Text #16

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.8866. Min Act: -0.0000

Data Index: 187393 (The Pile)

Max Activating Token Index: 86

Text #17

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.8339. Min Act: -0.0000

Data Index: 1976012 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.6610. Min Act: -0.0000

Data Index: 1379447 (The Pile)

Max Activating Token Index: 339

Text #19

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9806. Min Act: -0.0000

Data Index: 1197269 (The Pile)

Max Activating Token Index: 214