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

Dataset: The Pile

Neuron 3111 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: 0.3439. Min Range: -0.3439

Max Act: 0.3439. Min Act: -0.0000

Data Index: 441580 (The Pile)

Max Activating Token Index: 728

Text #1

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1691772 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2940. Min Act: -0.0000

Data Index: 1687532 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2953. Min Act: -0.0000

Data Index: 1188787 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1443907 (The Pile)

Max Activating Token Index: 621

Text #5

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1506012 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1315250 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2661. Min Act: -0.0000

Data Index: 286824 (The Pile)

Max Activating Token Index: 599

Text #8

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2515. Min Act: -0.0000

Data Index: 9452 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1902540 (The Pile)

Max Activating Token Index: 578

Text #10

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2738. Min Act: -0.0000

Data Index: 788812 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2625. Min Act: -0.0000

Data Index: 616053 (The Pile)

Max Activating Token Index: 788

Text #12

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2485. Min Act: -0.0000

Data Index: 1139718 (The Pile)

Max Activating Token Index: 489

Text #13

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2468. Min Act: -0.0000

Data Index: 290907 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1690580 (The Pile)

Max Activating Token Index: 928

Text #15

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2446. Min Act: -0.0000

Data Index: 122552 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1508787 (The Pile)

Max Activating Token Index: 943

Text #17

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2464. Min Act: -0.0000

Data Index: 431293 (The Pile)

Max Activating Token Index: 553

Text #18

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2526. Min Act: -0.0000

Data Index: 214379 (The Pile)

Max Activating Token Index: 897

Text #19

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2466. Min Act: -0.0000

Data Index: 779308 (The Pile)

Max Activating Token Index: 52