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

Dataset: The Pile

Neuron 488 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1575. Min Act: -0.0000

Data Index: 974052 (The Pile)

Max Activating Token Index: 231

Text #1

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0729. Min Act: -0.0000

Data Index: 541973 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1635. Min Act: -0.0000

Data Index: 516555 (The Pile)

Max Activating Token Index: 285

Text #3

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0726. Min Act: -0.0000

Data Index: 1286983 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0464. Min Act: -0.0000

Data Index: 226587 (The Pile)

Max Activating Token Index: 396

Text #5

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0677. Min Act: -0.0000

Data Index: 1395647 (The Pile)

Max Activating Token Index: 139

Text #6

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0896. Min Act: -0.0000

Data Index: 1731403 (The Pile)

Max Activating Token Index: 651

Text #7

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0792. Min Act: -0.0000

Data Index: 1024156 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1353537 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0743. Min Act: -0.0000

Data Index: 802284 (The Pile)

Max Activating Token Index: 365

Text #10

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0563. Min Act: -0.0000

Data Index: 593814 (The Pile)

Max Activating Token Index: 201

Text #11

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.9868. Min Act: -0.0000

Data Index: 1506125 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0131. Min Act: -0.0000

Data Index: 1677293 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0066. Min Act: -0.0000

Data Index: 957863 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.9735. Min Act: -0.0000

Data Index: 568746 (The Pile)

Max Activating Token Index: 338

Text #15

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0303. Min Act: -0.0000

Data Index: 1895388 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0692. Min Act: -0.0000

Data Index: 724094 (The Pile)

Max Activating Token Index: 277

Text #17

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1994429 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.9097. Min Act: -0.0000

Data Index: 15869 (The Pile)

Max Activating Token Index: 40

Text #19

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.9779. Min Act: -0.0000

Data Index: 88456 (The Pile)

Max Activating Token Index: 623