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

Dataset: The Pile

Neuron 1611 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.5411. Min Act: -0.0000

Data Index: 783739 (The Pile)

Max Activating Token Index: 237

Text #1

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.4719. Min Act: -0.0000

Data Index: 1889038 (The Pile)

Max Activating Token Index: 736

Text #2

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.0700. Min Act: 0.0000

Data Index: 1538412 (The Pile)

Max Activating Token Index: 275

Text #3

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.2051. Min Act: 0.0000

Data Index: 457776 (The Pile)

Max Activating Token Index: 594

Text #4

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1346034 (The Pile)

Max Activating Token Index: 384

Text #5

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1538648 (The Pile)

Max Activating Token Index: 911

Text #6

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.9477. Min Act: -0.0000

Data Index: 1227191 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.6473. Min Act: 0.0000

Data Index: 633650 (The Pile)

Max Activating Token Index: 486

Text #8

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.5762. Min Act: -0.0000

Data Index: 262344 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.6739. Min Act: -0.0000

Data Index: 758992 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1541590 (The Pile)

Max Activating Token Index: 867

Text #11

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.4661. Min Act: 0.0000

Data Index: 1972831 (The Pile)

Max Activating Token Index: 274

Text #12

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1579013 (The Pile)

Max Activating Token Index: 594

Text #13

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.4409. Min Act: 0.0000

Data Index: 382742 (The Pile)

Max Activating Token Index: 605

Text #14

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1145129 (The Pile)

Max Activating Token Index: 319

Text #15

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.4126. Min Act: 0.0000

Data Index: 491422 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.4403. Min Act: -0.0000

Data Index: 996339 (The Pile)

Max Activating Token Index: 516

Text #17

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1833098 (The Pile)

Max Activating Token Index: 636

Text #18

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.3684. Min Act: 0.0000

Data Index: 1478792 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 1.5411. Min Range: -1.5411

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1290377 (The Pile)

Max Activating Token Index: 309