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

Dataset: The Pile

Neuron 1520 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: 0.6161. Min Range: -0.6161

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1989635 (The Pile)

Max Activating Token Index: 606

Text #1

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.6161. Min Act: -0.0000

Data Index: 1497649 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5586. Min Act: -0.0000

Data Index: 324744 (The Pile)

Max Activating Token Index: 774

Text #3

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1939794 (The Pile)

Max Activating Token Index: 237

Text #4

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1859233 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4730. Min Act: -0.0000

Data Index: 367859 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4212. Min Act: -0.0000

Data Index: 200944 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4217. Min Act: -0.0000

Data Index: 700746 (The Pile)

Max Activating Token Index: 992

Text #8

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1978416 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4309. Min Act: -0.0000

Data Index: 656699 (The Pile)

Max Activating Token Index: 719

Text #10

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3735. Min Act: -0.0000

Data Index: 803290 (The Pile)

Max Activating Token Index: 881

Text #11

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4048. Min Act: -0.0000

Data Index: 920320 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4301. Min Act: -0.0000

Data Index: 167261 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4249. Min Act: -0.0000

Data Index: 847638 (The Pile)

Max Activating Token Index: 951

Text #14

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1024768 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1418724 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1460138 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3741. Min Act: -0.0000

Data Index: 455485 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1101645 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3711. Min Act: -0.0000

Data Index: 766259 (The Pile)

Max Activating Token Index: 63