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

Dataset: The Pile

Neuron 1122 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1809949 (The Pile)

Max Activating Token Index: 591

Text #1

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0571. Min Act: -0.0000

Data Index: 875856 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0478. Min Act: -0.0000

Data Index: 755332 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0415. Min Act: -0.0000

Data Index: 414507 (The Pile)

Max Activating Token Index: 981

Text #4

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1926066 (The Pile)

Max Activating Token Index: 804

Text #5

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0451. Min Act: -0.0000

Data Index: 543162 (The Pile)

Max Activating Token Index: 778

Text #6

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0390. Min Act: -0.0000

Data Index: 1975574 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0443. Min Act: -0.0000

Data Index: 1082595 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0370. Min Act: -0.0000

Data Index: 665457 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0383. Min Act: 0.0000

Data Index: 1996902 (The Pile)

Max Activating Token Index: 248

Text #10

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0383. Min Act: -0.0000

Data Index: 862503 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0360. Min Act: -0.0000

Data Index: 137837 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0342. Min Act: -0.0000

Data Index: 464317 (The Pile)

Max Activating Token Index: 414

Text #13

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0395. Min Act: -0.0000

Data Index: 1899648 (The Pile)

Max Activating Token Index: 179

Text #14

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0370. Min Act: -0.0000

Data Index: 903814 (The Pile)

Max Activating Token Index: 267

Text #15

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0373. Min Act: -0.0000

Data Index: 1322206 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1715328 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1059376 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1311257 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1520380 (The Pile)

Max Activating Token Index: 551