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

Dataset: The Pile

Neuron 677 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2716. Min Act: -0.0000

Data Index: 404688 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2742. Min Act: -0.0000

Data Index: 636125 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2829. Min Act: -0.0000

Data Index: 46930 (The Pile)

Max Activating Token Index: 7

Text #3

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2603. Min Act: -0.0000

Data Index: 503640 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1434109 (The Pile)

Max Activating Token Index: 418

Text #5

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2627. Min Act: -0.0000

Data Index: 523194 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1713181 (The Pile)

Max Activating Token Index: 693

Text #7

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1492425 (The Pile)

Max Activating Token Index: 274

Text #8

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1461823 (The Pile)

Max Activating Token Index: 707

Text #9

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2657. Min Act: -0.0000

Data Index: 1914090 (The Pile)

Max Activating Token Index: 770

Text #10

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2551. Min Act: -0.0000

Data Index: 982977 (The Pile)

Max Activating Token Index: 381

Text #11

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2382. Min Act: -0.0000

Data Index: 384400 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1386763 (The Pile)

Max Activating Token Index: 794

Text #13

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1811549 (The Pile)

Max Activating Token Index: 706

Text #14

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2485. Min Act: -0.0000

Data Index: 874550 (The Pile)

Max Activating Token Index: 150

Text #15

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2477. Min Act: 0.0000

Data Index: 1239722 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2343. Min Act: -0.0000

Data Index: 340017 (The Pile)

Max Activating Token Index: 658

Text #17

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2401. Min Act: -0.0000

Data Index: 283900 (The Pile)

Max Activating Token Index: 932

Text #18

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2390. Min Act: -0.0000

Data Index: 822764 (The Pile)

Max Activating Token Index: 895

Text #19

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1487589 (The Pile)

Max Activating Token Index: 412