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

Dataset: The Pile

Neuron 4093 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: 0.8347. Min Range: -0.8347

Max Act: 0.8347. Min Act: -0.0000

Data Index: 742247 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.7808. Min Act: -0.0000

Data Index: 437357 (The Pile)

Max Activating Token Index: 178

Text #2

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.7346. Min Act: 0.0000

Data Index: 1637538 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.7085. Min Act: -0.0000

Data Index: 647144 (The Pile)

Max Activating Token Index: 355

Text #4

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.6990. Min Act: -0.0000

Data Index: 1316044 (The Pile)

Max Activating Token Index: 776

Text #5

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.6352. Min Act: -0.0000

Data Index: 65392 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.7062. Min Act: -0.0000

Data Index: 311957 (The Pile)

Max Activating Token Index: 891

Text #7

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1713197 (The Pile)

Max Activating Token Index: 484

Text #8

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.6397. Min Act: -0.0000

Data Index: 972595 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.6597. Min Act: -0.0000

Data Index: 357166 (The Pile)

Max Activating Token Index: 970

Text #10

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.6623. Min Act: -0.0000

Data Index: 424831 (The Pile)

Max Activating Token Index: 482

Text #11

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1308566 (The Pile)

Max Activating Token Index: 974

Text #12

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.7379. Min Act: -0.0000

Data Index: 529667 (The Pile)

Max Activating Token Index: 80

Text #13

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1014296 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.6670. Min Act: 0.0000

Data Index: 697934 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.6593. Min Act: -0.0000

Data Index: 567574 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.5934. Min Act: -0.0000

Data Index: 737809 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.6475. Min Act: -0.0000

Data Index: 197395 (The Pile)

Max Activating Token Index: 561

Text #18

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1270417 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 0.8347. Min Range: -0.8347

Max Act: 0.6089. Min Act: -0.0000

Data Index: 760730 (The Pile)

Max Activating Token Index: 653