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

Dataset: The Pile

Neuron 4244 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: 0.6411. Min Range: -0.6411

Max Act: 0.6085. Min Act: -0.0000

Data Index: 945594 (The Pile)

Max Activating Token Index: 414

Text #1

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1181136 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1154833 (The Pile)

Max Activating Token Index: 435

Text #3

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1260070 (The Pile)

Max Activating Token Index: 288

Text #4

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5657. Min Act: -0.0000

Data Index: 999505 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5404. Min Act: -0.0000

Data Index: 1500701 (The Pile)

Max Activating Token Index: 412

Text #6

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1936269 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1749689 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1163488 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1889182 (The Pile)

Max Activating Token Index: 599

Text #10

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5560. Min Act: -0.0000

Data Index: 847604 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1320844 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1369973 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1371593 (The Pile)

Max Activating Token Index: 225

Text #14

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4591. Min Act: 0.0000

Data Index: 711837 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5161. Min Act: -0.0000

Data Index: 905148 (The Pile)

Max Activating Token Index: 599

Text #16

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1166779 (The Pile)

Max Activating Token Index: 804

Text #17

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4656. Min Act: -0.0000

Data Index: 401837 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1462363 (The Pile)

Max Activating Token Index: 889

Text #19

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4614. Min Act: -0.0000

Data Index: 529058 (The Pile)

Max Activating Token Index: 546