Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2098 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.7418. Min Act: -0.0000

Data Index: 635016 (The Pile)

Max Activating Token Index: 489

Text #1

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.7324. Min Act: -0.0000

Data Index: 237665 (The Pile)

Max Activating Token Index: 160

Text #2

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1523200 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1743583 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6547. Min Act: -0.0000

Data Index: 51088 (The Pile)

Max Activating Token Index: 645

Text #5

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6316. Min Act: -0.0000

Data Index: 963874 (The Pile)

Max Activating Token Index: 586

Text #6

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6135. Min Act: -0.0000

Data Index: 583487 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1400303 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1397966 (The Pile)

Max Activating Token Index: 410

Text #9

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1155780 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6010. Min Act: -0.0000

Data Index: 502389 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5667. Min Act: -0.0000

Data Index: 642326 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5761. Min Act: -0.0000

Data Index: 225755 (The Pile)

Max Activating Token Index: 977

Text #13

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5755. Min Act: -0.0000

Data Index: 739519 (The Pile)

Max Activating Token Index: 446

Text #14

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1187508 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1932489 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1715752 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1929414 (The Pile)

Max Activating Token Index: 184

Text #18

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5610. Min Act: -0.0000

Data Index: 599644 (The Pile)

Max Activating Token Index: 933

Text #19

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5580. Min Act: -0.0000

Data Index: 511739 (The Pile)

Max Activating Token Index: 21