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

Dataset: The Pile

Neuron 1292 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6972. Min Range: -3.6972

Max Act: 3.6972. Min Act: -0.0000

Data Index: 299721 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 3.6972. Min Range: -3.6972

Max Act: 3.3712. Min Act: -0.0000

Data Index: 128900 (The Pile)

Max Activating Token Index: 437

Text #2

Max Range: 3.6972. Min Range: -3.6972

Max Act: 2.3029. Min Act: -0.0000

Data Index: 1560271 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 3.6972. Min Range: -3.6972

Max Act: 3.2139. Min Act: -0.0000

Data Index: 1732203 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 3.6972. Min Range: -3.6972

Max Act: 3.0825. Min Act: -0.0000

Data Index: 1157675 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 3.6972. Min Range: -3.6972

Max Act: 2.7025. Min Act: -0.0000

Data Index: 736835 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 3.6972. Min Range: -3.6972

Max Act: 3.4839. Min Act: -0.0000

Data Index: 1810732 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 3.6972. Min Range: -3.6972

Max Act: 3.1436. Min Act: -0.0000

Data Index: 69121 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 3.6972. Min Range: -3.6972

Max Act: 2.8433. Min Act: -0.0000

Data Index: 1439556 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 3.6972. Min Range: -3.6972

Max Act: 3.0651. Min Act: -0.0000

Data Index: 743318 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 3.6972. Min Range: -3.6972

Max Act: 2.9598. Min Act: -0.0000

Data Index: 690525 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 3.6972. Min Range: -3.6972

Max Act: 2.9714. Min Act: -0.0000

Data Index: 1988951 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 3.6972. Min Range: -3.6972

Max Act: 3.5703. Min Act: -0.0000

Data Index: 1878984 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 3.6972. Min Range: -3.6972

Max Act: 3.0350. Min Act: -0.0000

Data Index: 1387543 (The Pile)

Max Activating Token Index: 140

Text #14

Max Range: 3.6972. Min Range: -3.6972

Max Act: 2.9242. Min Act: -0.0000

Data Index: 1692623 (The Pile)

Max Activating Token Index: 881

Text #15

Max Range: 3.6972. Min Range: -3.6972

Max Act: 3.0366. Min Act: -0.0000

Data Index: 1442390 (The Pile)

Max Activating Token Index: 339

Text #16

Max Range: 3.6972. Min Range: -3.6972

Max Act: 2.8199. Min Act: -0.0000

Data Index: 1241215 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 3.6972. Min Range: -3.6972

Max Act: 2.8591. Min Act: -0.0000

Data Index: 1703721 (The Pile)

Max Activating Token Index: 398

Text #18

Max Range: 3.6972. Min Range: -3.6972

Max Act: 3.0775. Min Act: -0.0000

Data Index: 1164891 (The Pile)

Max Activating Token Index: 829

Text #19

Max Range: 3.6972. Min Range: -3.6972

Max Act: 2.8505. Min Act: -0.0000

Data Index: 81478 (The Pile)

Max Activating Token Index: 311