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

Dataset: The Pile

Neuron 3724 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: 3.5230. Min Range: -3.5230

Max Act: 3.5230. Min Act: -0.0000

Data Index: 1664039 (The Pile)

Max Activating Token Index: 567

Text #1

Max Range: 3.5230. Min Range: -3.5230

Max Act: 2.7749. Min Act: -0.0000

Data Index: 402738 (The Pile)

Max Activating Token Index: 57

Text #2

Max Range: 3.5230. Min Range: -3.5230

Max Act: 2.5236. Min Act: -0.0000

Data Index: 1479521 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 3.5230. Min Range: -3.5230

Max Act: 2.3515. Min Act: -0.0000

Data Index: 840053 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 3.5230. Min Range: -3.5230

Max Act: 1.9777. Min Act: -0.0000

Data Index: 1214772 (The Pile)

Max Activating Token Index: 34

Text #5

Max Range: 3.5230. Min Range: -3.5230

Max Act: 2.1965. Min Act: -0.0000

Data Index: 802888 (The Pile)

Max Activating Token Index: 485

Text #6

Max Range: 3.5230. Min Range: -3.5230

Max Act: 2.0694. Min Act: -0.0000

Data Index: 1166410 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 3.5230. Min Range: -3.5230

Max Act: 2.0453. Min Act: -0.0000

Data Index: 1210496 (The Pile)

Max Activating Token Index: 903

Text #8

Max Range: 3.5230. Min Range: -3.5230

Max Act: 2.0225. Min Act: -0.0000

Data Index: 1511259 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 3.5230. Min Range: -3.5230

Max Act: 1.8117. Min Act: -0.0000

Data Index: 1494666 (The Pile)

Max Activating Token Index: 141

Text #10

Max Range: 3.5230. Min Range: -3.5230

Max Act: 2.0033. Min Act: -0.0000

Data Index: 1872720 (The Pile)

Max Activating Token Index: 445

Text #11

Max Range: 3.5230. Min Range: -3.5230

Max Act: 2.0931. Min Act: -0.0000

Data Index: 1451024 (The Pile)

Max Activating Token Index: 335

Text #12

Max Range: 3.5230. Min Range: -3.5230

Max Act: 1.8530. Min Act: -0.0000

Data Index: 1747326 (The Pile)

Max Activating Token Index: 523

Text #13

Max Range: 3.5230. Min Range: -3.5230

Max Act: 2.0316. Min Act: -0.0000

Data Index: 51538 (The Pile)

Max Activating Token Index: 569

Text #14

Max Range: 3.5230. Min Range: -3.5230

Max Act: 1.7289. Min Act: -0.0000

Data Index: 317309 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 3.5230. Min Range: -3.5230

Max Act: 1.8356. Min Act: -0.0000

Data Index: 97456 (The Pile)

Max Activating Token Index: 494

Text #16

Max Range: 3.5230. Min Range: -3.5230

Max Act: 1.8218. Min Act: -0.0000

Data Index: 1709301 (The Pile)

Max Activating Token Index: 321

Text #17

Max Range: 3.5230. Min Range: -3.5230

Max Act: 1.9328. Min Act: -0.0000

Data Index: 1224078 (The Pile)

Max Activating Token Index: 132

Text #18

Max Range: 3.5230. Min Range: -3.5230

Max Act: 1.8044. Min Act: -0.0000

Data Index: 772384 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 3.5230. Min Range: -3.5230

Max Act: 1.9871. Min Act: -0.0000

Data Index: 584412 (The Pile)

Max Activating Token Index: 893