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

Dataset: The Pile

Neuron 774 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: 1.5661. Min Range: -1.5661

Max Act: 1.5661. Min Act: -0.0000

Data Index: 155106 (The Pile)

Max Activating Token Index: 583

Text #1

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.4974. Min Act: -0.0000

Data Index: 1587423 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.3946. Min Act: 0.0000

Data Index: 492508 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.1570. Min Act: -0.0000

Data Index: 1552420 (The Pile)

Max Activating Token Index: 873

Text #4

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.2033. Min Act: -0.0000

Data Index: 670745 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.0734. Min Act: -0.0000

Data Index: 925659 (The Pile)

Max Activating Token Index: 725

Text #6

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.0289. Min Act: -0.0000

Data Index: 838971 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.0562. Min Act: -0.0000

Data Index: 576955 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.0312. Min Act: -0.0000

Data Index: 550489 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.0154. Min Act: -0.0000

Data Index: 933702 (The Pile)

Max Activating Token Index: 346

Text #10

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.0131. Min Act: -0.0000

Data Index: 1691375 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9723. Min Act: -0.0000

Data Index: 860868 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9994. Min Act: -0.0000

Data Index: 211134 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9598. Min Act: -0.0000

Data Index: 110407 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9947. Min Act: -0.0000

Data Index: 888903 (The Pile)

Max Activating Token Index: 814

Text #15

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1776540 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9937. Min Act: 0.0000

Data Index: 1432871 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1647465 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1473564 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1200292 (The Pile)

Max Activating Token Index: 362