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

Dataset: The Pile

Neuron 1297 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.1235. Min Act: -0.0000

Data Index: 1563642 (The Pile)

Max Activating Token Index: 229

Text #1

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.0756. Min Act: -0.0000

Data Index: 124530 (The Pile)

Max Activating Token Index: 215

Text #2

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.0327. Min Act: -0.0000

Data Index: 1743101 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.3061. Min Act: -0.0000

Data Index: 1114093 (The Pile)

Max Activating Token Index: 460

Text #4

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.1885. Min Act: -0.0000

Data Index: 1105449 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.0491. Min Act: -0.0000

Data Index: 1578250 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.1379. Min Act: -0.0000

Data Index: 345125 (The Pile)

Max Activating Token Index: 175

Text #7

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.1186. Min Act: -0.0000

Data Index: 523606 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.1205. Min Act: -0.0000

Data Index: 1061099 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.7910. Min Act: -0.0000

Data Index: 1601749 (The Pile)

Max Activating Token Index: 581

Text #10

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.0445. Min Act: -0.0000

Data Index: 835151 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.0756. Min Act: -0.0000

Data Index: 440928 (The Pile)

Max Activating Token Index: 536

Text #12

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.9909. Min Act: -0.0000

Data Index: 512973 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.1188. Min Act: -0.0000

Data Index: 1736353 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.8872. Min Act: -0.0000

Data Index: 1642743 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.8233. Min Act: -0.0000

Data Index: 1519337 (The Pile)

Max Activating Token Index: 321

Text #16

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.8386. Min Act: -0.0000

Data Index: 1805966 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.9483. Min Act: -0.0000

Data Index: 1029602 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.6976. Min Act: -0.0000

Data Index: 1564258 (The Pile)

Max Activating Token Index: 542

Text #19

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.0954. Min Act: -0.0000

Data Index: 26816 (The Pile)

Max Activating Token Index: 314