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

Dataset: The Pile

Neuron 1573 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: 1.4532. Min Range: -1.4532

Max Act: 1.4532. Min Act: -0.0000

Data Index: 525765 (The Pile)

Max Activating Token Index: 224

Text #1

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.3170. Min Act: -0.0000

Data Index: 1944993 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2224. Min Act: -0.0000

Data Index: 1920538 (The Pile)

Max Activating Token Index: 244

Text #3

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2086. Min Act: -0.0000

Data Index: 1574231 (The Pile)

Max Activating Token Index: 191

Text #4

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2202. Min Act: -0.0000

Data Index: 308254 (The Pile)

Max Activating Token Index: 504

Text #5

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1580. Min Act: -0.0000

Data Index: 1614816 (The Pile)

Max Activating Token Index: 477

Text #6

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2196. Min Act: -0.0000

Data Index: 453338 (The Pile)

Max Activating Token Index: 280

Text #7

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.0770. Min Act: -0.0000

Data Index: 1941808 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1302. Min Act: -0.0000

Data Index: 1001987 (The Pile)

Max Activating Token Index: 673

Text #9

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2321. Min Act: -0.0000

Data Index: 225733 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1310. Min Act: -0.0000

Data Index: 1891261 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1867. Min Act: -0.0000

Data Index: 1061255 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1191. Min Act: -0.0000

Data Index: 1727947 (The Pile)

Max Activating Token Index: 731

Text #13

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1017. Min Act: -0.0000

Data Index: 1214696 (The Pile)

Max Activating Token Index: 623

Text #14

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.0930. Min Act: -0.0000

Data Index: 884161 (The Pile)

Max Activating Token Index: 265

Text #15

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.0844. Min Act: -0.0000

Data Index: 60620 (The Pile)

Max Activating Token Index: 36

Text #16

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1106. Min Act: -0.0000

Data Index: 960107 (The Pile)

Max Activating Token Index: 144

Text #17

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.0935. Min Act: -0.0000

Data Index: 263407 (The Pile)

Max Activating Token Index: 883

Text #18

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1387283 (The Pile)

Max Activating Token Index: 223

Text #19

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.0931. Min Act: -0.0000

Data Index: 1908475 (The Pile)

Max Activating Token Index: 379