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

Dataset: The Pile

Neuron 3989 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.2632. Min Act: -0.0000

Data Index: 1115341 (The Pile)

Max Activating Token Index: 255

Text #1

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.1213. Min Act: -0.0000

Data Index: 1681779 (The Pile)

Max Activating Token Index: 969

Text #2

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1623606 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.0450. Min Act: -0.0000

Data Index: 1732308 (The Pile)

Max Activating Token Index: 418

Text #4

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.0358. Min Act: -0.0000

Data Index: 1976473 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.0442. Min Act: -0.0000

Data Index: 178051 (The Pile)

Max Activating Token Index: 691

Text #6

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.0185. Min Act: -0.0000

Data Index: 866019 (The Pile)

Max Activating Token Index: 796

Text #7

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.0784. Min Act: -0.0000

Data Index: 301949 (The Pile)

Max Activating Token Index: 702

Text #8

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.0092. Min Act: 0.0000

Data Index: 1641367 (The Pile)

Max Activating Token Index: 431

Text #9

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1856411 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1012713 (The Pile)

Max Activating Token Index: 997

Text #11

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.0025. Min Act: -0.0000

Data Index: 443152 (The Pile)

Max Activating Token Index: 216

Text #12

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.9960. Min Act: -0.0000

Data Index: 812551 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.9992. Min Act: -0.0000

Data Index: 1169558 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.9803. Min Act: -0.0000

Data Index: 662755 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.9819. Min Act: -0.0000

Data Index: 91161 (The Pile)

Max Activating Token Index: 888

Text #16

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.8859. Min Act: -0.0000

Data Index: 880355 (The Pile)

Max Activating Token Index: 591

Text #17

Max Range: 1.2632. Min Range: -1.2632

Max Act: 1.0138. Min Act: -0.0000

Data Index: 761378 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1982936 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 1.2632. Min Range: -1.2632

Max Act: 0.9260. Min Act: -0.0000

Data Index: 850663 (The Pile)

Max Activating Token Index: 213