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

Dataset: The Pile

Neuron 4098 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.8471. Min Act: -0.0000

Data Index: 819186 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7858. Min Act: -0.0000

Data Index: 97163 (The Pile)

Max Activating Token Index: 17

Text #2

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.8057. Min Act: -0.0000

Data Index: 958462 (The Pile)

Max Activating Token Index: 231

Text #3

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7433. Min Act: -0.0000

Data Index: 193737 (The Pile)

Max Activating Token Index: 310

Text #4

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7752. Min Act: -0.0000

Data Index: 696169 (The Pile)

Max Activating Token Index: 340

Text #5

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7826. Min Act: -0.0000

Data Index: 162763 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7707. Min Act: -0.0000

Data Index: 466457 (The Pile)

Max Activating Token Index: 353

Text #7

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1355274 (The Pile)

Max Activating Token Index: 356

Text #8

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1780424 (The Pile)

Max Activating Token Index: 1015

Text #9

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1694285 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1946659 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1807897 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1369524 (The Pile)

Max Activating Token Index: 363

Text #13

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7225. Min Act: -0.0000

Data Index: 503626 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1049259 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6664. Min Act: -0.0000

Data Index: 850410 (The Pile)

Max Activating Token Index: 614

Text #16

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7405. Min Act: -0.0000

Data Index: 1511427 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7198. Min Act: -0.0000

Data Index: 193154 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1371242 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6853. Min Act: -0.0000

Data Index: 373600 (The Pile)

Max Activating Token Index: 487