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

Dataset: The Pile

Neuron 2585 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.1972. Min Act: -0.0000

Data Index: 1555679 (The Pile)

Max Activating Token Index: 64

Text #1

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.8541. Min Act: -0.0000

Data Index: 880129 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.7111. Min Act: -0.0000

Data Index: 1048804 (The Pile)

Max Activating Token Index: 484

Text #3

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.4936. Min Act: -0.0000

Data Index: 134331 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.2241. Min Act: -0.0000

Data Index: 1122576 (The Pile)

Max Activating Token Index: 846

Text #5

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.2913. Min Act: -0.0000

Data Index: 1904644 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.2793. Min Act: -0.0000

Data Index: 367834 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.1484. Min Act: -0.0000

Data Index: 851 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.1196. Min Act: -0.0000

Data Index: 750440 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.1109. Min Act: -0.0000

Data Index: 967540 (The Pile)

Max Activating Token Index: 600

Text #10

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.2274. Min Act: -0.0000

Data Index: 1900874 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.2396. Min Act: -0.0000

Data Index: 245411 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.3294. Min Act: -0.0000

Data Index: 184915 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.0922. Min Act: -0.0000

Data Index: 576666 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.3190. Min Act: -0.0000

Data Index: 1952271 (The Pile)

Max Activating Token Index: 312

Text #15

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.0717. Min Act: -0.0000

Data Index: 84556 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.4303. Min Act: -0.0000

Data Index: 1578745 (The Pile)

Max Activating Token Index: 889

Text #17

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.0529. Min Act: -0.0000

Data Index: 754318 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.1567. Min Act: -0.0000

Data Index: 252459 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 3.1972. Min Range: -3.1972

Max Act: 2.1487. Min Act: -0.0000

Data Index: 1351551 (The Pile)

Max Activating Token Index: 556