Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3057 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3242. Min Act: -0.0000

Data Index: 485995 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3442. Min Act: -0.0001

Data Index: 324822 (The Pile)

Max Activating Token Index: 952

Text #2

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3008. Min Act: -0.0000

Data Index: 551495 (The Pile)

Max Activating Token Index: 28

Text #3

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1540335 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2884. Min Act: -0.0000

Data Index: 956660 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2874. Min Act: -0.0001

Data Index: 687684 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1910549 (The Pile)

Max Activating Token Index: 844

Text #7

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2602. Min Act: -0.0001

Data Index: 1500612 (The Pile)

Max Activating Token Index: 386

Text #8

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2612. Min Act: -0.0000

Data Index: 569879 (The Pile)

Max Activating Token Index: 338

Text #9

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2446. Min Act: -0.0000

Data Index: 276655 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2605. Min Act: -0.0000

Data Index: 504954 (The Pile)

Max Activating Token Index: 782

Text #11

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2418. Min Act: -0.0000

Data Index: 269398 (The Pile)

Max Activating Token Index: 926

Text #12

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2566. Min Act: -0.0000

Data Index: 120269 (The Pile)

Max Activating Token Index: 215

Text #13

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2310. Min Act: -0.0000

Data Index: 744510 (The Pile)

Max Activating Token Index: 612

Text #14

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2551. Min Act: -0.0001

Data Index: 1221005 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2472. Min Act: -0.0000

Data Index: 761006 (The Pile)

Max Activating Token Index: 225

Text #16

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2419. Min Act: -0.0001

Data Index: 757509 (The Pile)

Max Activating Token Index: 407

Text #17

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1589522 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1755799 (The Pile)

Max Activating Token Index: 306

Text #19

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1501356 (The Pile)

Max Activating Token Index: 323