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

Dataset: The Pile

Neuron 350 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: 1.4668. Min Range: -1.4668

Max Act: 1.4668. Min Act: -0.0000

Data Index: 303272 (The Pile)

Max Activating Token Index: 215

Text #1

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.3213. Min Act: -0.0000

Data Index: 761053 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.3913. Min Act: -0.0000

Data Index: 302493 (The Pile)

Max Activating Token Index: 320

Text #3

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2727. Min Act: -0.0000

Data Index: 864080 (The Pile)

Max Activating Token Index: 58

Text #4

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.3381. Min Act: -0.0000

Data Index: 1663166 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2661. Min Act: -0.0000

Data Index: 830672 (The Pile)

Max Activating Token Index: 929

Text #6

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1371328 (The Pile)

Max Activating Token Index: 204

Text #7

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2525. Min Act: -0.0000

Data Index: 518042 (The Pile)

Max Activating Token Index: 432

Text #8

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1722. Min Act: -0.0000

Data Index: 285815 (The Pile)

Max Activating Token Index: 841

Text #9

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.3548. Min Act: -0.0000

Data Index: 1849359 (The Pile)

Max Activating Token Index: 748

Text #10

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2301. Min Act: -0.0000

Data Index: 1958932 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2983. Min Act: -0.0000

Data Index: 1720511 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2445. Min Act: -0.0000

Data Index: 676980 (The Pile)

Max Activating Token Index: 895

Text #13

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2326. Min Act: -0.0000

Data Index: 1635203 (The Pile)

Max Activating Token Index: 983

Text #14

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2268. Min Act: -0.0000

Data Index: 1340551 (The Pile)

Max Activating Token Index: 102

Text #15

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1515. Min Act: -0.0000

Data Index: 230703 (The Pile)

Max Activating Token Index: 691

Text #16

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1592. Min Act: -0.0000

Data Index: 906621 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1446. Min Act: -0.0000

Data Index: 413961 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.0646. Min Act: -0.0000

Data Index: 1829718 (The Pile)

Max Activating Token Index: 944

Text #19

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1975. Min Act: -0.0000

Data Index: 1889915 (The Pile)

Max Activating Token Index: 222