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

Dataset: The Pile

Neuron 3286 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: 1.2639. Min Range: -1.2639

Max Act: 1.2639. Min Act: -0.0000

Data Index: 589281 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 1.2639. Min Range: -1.2639

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1106265 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 1.2639. Min Range: -1.2639

Max Act: 1.1108. Min Act: -0.0000

Data Index: 1816646 (The Pile)

Max Activating Token Index: 697

Text #3

Max Range: 1.2639. Min Range: -1.2639

Max Act: 1.0110. Min Act: -0.0000

Data Index: 1704790 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1687137 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1010738 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.9517. Min Act: -0.0000

Data Index: 913235 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.8355. Min Act: -0.0000

Data Index: 367986 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.8589. Min Act: -0.0000

Data Index: 780031 (The Pile)

Max Activating Token Index: 928

Text #9

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.8933. Min Act: -0.0000

Data Index: 1074073 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1412154 (The Pile)

Max Activating Token Index: 201

Text #11

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.8733. Min Act: -0.0000

Data Index: 268713 (The Pile)

Max Activating Token Index: 598

Text #12

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.8712. Min Act: -0.0000

Data Index: 354086 (The Pile)

Max Activating Token Index: 916

Text #13

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.8345. Min Act: -0.0000

Data Index: 1604346 (The Pile)

Max Activating Token Index: 841

Text #14

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.8250. Min Act: -0.0000

Data Index: 1211413 (The Pile)

Max Activating Token Index: 243

Text #15

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1663815 (The Pile)

Max Activating Token Index: 615

Text #16

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1779135 (The Pile)

Max Activating Token Index: 373

Text #17

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1629850 (The Pile)

Max Activating Token Index: 798

Text #18

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1939081 (The Pile)

Max Activating Token Index: 521

Text #19

Max Range: 1.2639. Min Range: -1.2639

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1133922 (The Pile)

Max Activating Token Index: 516