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

Dataset: The Pile

Neuron 2034 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7965. Min Range: -7.7965

Max Act: 7.7965. Min Act: -0.0000

Data Index: 64158 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 7.7965. Min Range: -7.7965

Max Act: 5.9080. Min Act: -0.0000

Data Index: 592304 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 7.7965. Min Range: -7.7965

Max Act: 6.1742. Min Act: -0.0000

Data Index: 320052 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 7.7965. Min Range: -7.7965

Max Act: 6.6757. Min Act: -0.0000

Data Index: 116943 (The Pile)

Max Activating Token Index: 823

Text #4

Max Range: 7.7965. Min Range: -7.7965

Max Act: 6.2227. Min Act: -0.0000

Data Index: 1866800 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 7.7965. Min Range: -7.7965

Max Act: 5.9411. Min Act: -0.0000

Data Index: 1708387 (The Pile)

Max Activating Token Index: 378

Text #6

Max Range: 7.7965. Min Range: -7.7965

Max Act: 5.8881. Min Act: -0.0000

Data Index: 1039167 (The Pile)

Max Activating Token Index: 626

Text #7

Max Range: 7.7965. Min Range: -7.7965

Max Act: 6.3423. Min Act: -0.0000

Data Index: 1948255 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 7.7965. Min Range: -7.7965

Max Act: 6.1351. Min Act: -0.0000

Data Index: 104795 (The Pile)

Max Activating Token Index: 943

Text #9

Max Range: 7.7965. Min Range: -7.7965

Max Act: 6.0812. Min Act: -0.0000

Data Index: 1364474 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 7.7965. Min Range: -7.7965

Max Act: 5.9022. Min Act: -0.0000

Data Index: 1769155 (The Pile)

Max Activating Token Index: 57

Text #11

Max Range: 7.7965. Min Range: -7.7965

Max Act: 5.9815. Min Act: -0.0000

Data Index: 617739 (The Pile)

Max Activating Token Index: 229

Text #12

Max Range: 7.7965. Min Range: -7.7965

Max Act: 5.9759. Min Act: -0.0000

Data Index: 1252925 (The Pile)

Max Activating Token Index: 956

Text #13

Max Range: 7.7965. Min Range: -7.7965

Max Act: 6.1058. Min Act: -0.0000

Data Index: 1200107 (The Pile)

Max Activating Token Index: 815

Text #14

Max Range: 7.7965. Min Range: -7.7965

Max Act: 5.9413. Min Act: -0.0000

Data Index: 1242437 (The Pile)

Max Activating Token Index: 725

Text #15

Max Range: 7.7965. Min Range: -7.7965

Max Act: 5.9154. Min Act: -0.0000

Data Index: 620149 (The Pile)

Max Activating Token Index: 56

Text #16

Max Range: 7.7965. Min Range: -7.7965

Max Act: 5.9256. Min Act: -0.0000

Data Index: 622435 (The Pile)

Max Activating Token Index: 68

Text #17

Max Range: 7.7965. Min Range: -7.7965

Max Act: 5.9918. Min Act: -0.0000

Data Index: 354798 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 7.7965. Min Range: -7.7965

Max Act: 6.2582. Min Act: -0.0000

Data Index: 1426390 (The Pile)

Max Activating Token Index: 913

Text #19

Max Range: 7.7965. Min Range: -7.7965

Max Act: 5.8412. Min Act: -0.0000

Data Index: 816003 (The Pile)

Max Activating Token Index: 745