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

Dataset: The Pile

Neuron 3904 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.7681. Min Act: -0.0000

Data Index: 1523408 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1897727 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1017386 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1931079 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1027603 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6590. Min Act: -0.0000

Data Index: 247268 (The Pile)

Max Activating Token Index: 52

Text #6

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6359. Min Act: -0.0000

Data Index: 939406 (The Pile)

Max Activating Token Index: 379

Text #7

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1353764 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6463. Min Act: -0.0000

Data Index: 348945 (The Pile)

Max Activating Token Index: 499

Text #9

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6435. Min Act: -0.0000

Data Index: 844891 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6263. Min Act: -0.0000

Data Index: 74443 (The Pile)

Max Activating Token Index: 546

Text #11

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6023. Min Act: -0.0000

Data Index: 567101 (The Pile)

Max Activating Token Index: 699

Text #12

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6149. Min Act: -0.0000

Data Index: 522060 (The Pile)

Max Activating Token Index: 34

Text #13

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1401054 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1508243 (The Pile)

Max Activating Token Index: 365

Text #15

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6861. Min Act: -0.0000

Data Index: 697299 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6023. Min Act: -0.0000

Data Index: 266463 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6184. Min Act: -0.0000

Data Index: 532917 (The Pile)

Max Activating Token Index: 375

Text #18

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6188. Min Act: -0.0000

Data Index: 424487 (The Pile)

Max Activating Token Index: 138

Text #19

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5961. Min Act: -0.0000

Data Index: 762086 (The Pile)

Max Activating Token Index: 559