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

Dataset: The Pile

Neuron 3650 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: 1.2263. Min Range: -1.2263

Max Act: 1.1818. Min Act: -0.0000

Data Index: 385105 (The Pile)

Max Activating Token Index: 1012

Text #1

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.2263. Min Act: -0.0000

Data Index: 910945 (The Pile)

Max Activating Token Index: 75

Text #2

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.1045. Min Act: -0.0000

Data Index: 1831680 (The Pile)

Max Activating Token Index: 446

Text #3

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0882. Min Act: -0.0000

Data Index: 1532735 (The Pile)

Max Activating Token Index: 890

Text #4

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0545. Min Act: -0.0000

Data Index: 1045019 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9402. Min Act: -0.0000

Data Index: 1644374 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1839548 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0748. Min Act: -0.0000

Data Index: 407356 (The Pile)

Max Activating Token Index: 707

Text #8

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9093. Min Act: -0.0000

Data Index: 605268 (The Pile)

Max Activating Token Index: 257

Text #9

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9402. Min Act: -0.0000

Data Index: 771445 (The Pile)

Max Activating Token Index: 416

Text #10

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8997. Min Act: -0.0000

Data Index: 208518 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.1334. Min Act: -0.0000

Data Index: 1627549 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9167. Min Act: -0.0000

Data Index: 543283 (The Pile)

Max Activating Token Index: 248

Text #13

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8703. Min Act: 0.0000

Data Index: 1146970 (The Pile)

Max Activating Token Index: 736

Text #14

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9083. Min Act: -0.0000

Data Index: 169063 (The Pile)

Max Activating Token Index: 629

Text #15

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9271. Min Act: -0.0000

Data Index: 439832 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1443542 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1991940 (The Pile)

Max Activating Token Index: 434

Text #18

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1547184 (The Pile)

Max Activating Token Index: 910

Text #19

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1206566 (The Pile)

Max Activating Token Index: 214