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

Dataset: The Pile

Neuron 2253 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: 0.5796. Min Range: -0.5796

Max Act: 0.5796. Min Act: -0.0000

Data Index: 357999 (The Pile)

Max Activating Token Index: 420

Text #1

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.5151. Min Act: -0.0000

Data Index: 231398 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4984. Min Act: -0.0000

Data Index: 605087 (The Pile)

Max Activating Token Index: 291

Text #3

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4897. Min Act: -0.0000

Data Index: 205418 (The Pile)

Max Activating Token Index: 940

Text #4

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1871517 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4775. Min Act: -0.0000

Data Index: 641804 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1116546 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4586. Min Act: -0.0000

Data Index: 458133 (The Pile)

Max Activating Token Index: 390

Text #8

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4863. Min Act: -0.0000

Data Index: 913835 (The Pile)

Max Activating Token Index: 428

Text #9

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4705. Min Act: -0.0000

Data Index: 229591 (The Pile)

Max Activating Token Index: 251

Text #10

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1271636 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4457. Min Act: -0.0000

Data Index: 172691 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1354222 (The Pile)

Max Activating Token Index: 262

Text #13

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4517. Min Act: -0.0000

Data Index: 337467 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1917791 (The Pile)

Max Activating Token Index: 174

Text #15

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4381. Min Act: -0.0000

Data Index: 798197 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1294304 (The Pile)

Max Activating Token Index: 783

Text #17

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4400. Min Act: -0.0000

Data Index: 807703 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1922512 (The Pile)

Max Activating Token Index: 545

Text #19

Max Range: 0.5796. Min Range: -0.5796

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1174264 (The Pile)

Max Activating Token Index: 358