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

Dataset: The Pile

Neuron 2296 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: 3.9274. Min Range: -3.9274

Max Act: 3.9274. Min Act: -0.0000

Data Index: 1934995 (The Pile)

Max Activating Token Index: 690

Text #1

Max Range: 3.9274. Min Range: -3.9274

Max Act: 3.6977. Min Act: -0.0000

Data Index: 1544836 (The Pile)

Max Activating Token Index: 600

Text #2

Max Range: 3.9274. Min Range: -3.9274

Max Act: 3.8373. Min Act: -0.0000

Data Index: 387553 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 3.9274. Min Range: -3.9274

Max Act: 3.4734. Min Act: -0.0000

Data Index: 963456 (The Pile)

Max Activating Token Index: 232

Text #4

Max Range: 3.9274. Min Range: -3.9274

Max Act: 3.6141. Min Act: -0.0000

Data Index: 1705625 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 3.9274. Min Range: -3.9274

Max Act: 3.3507. Min Act: -0.0000

Data Index: 1368161 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 3.9274. Min Range: -3.9274

Max Act: 3.8754. Min Act: -0.0000

Data Index: 744289 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 3.9274. Min Range: -3.9274

Max Act: 3.3829. Min Act: -0.0000

Data Index: 711225 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 3.9274. Min Range: -3.9274

Max Act: 3.3473. Min Act: -0.0000

Data Index: 1683645 (The Pile)

Max Activating Token Index: 556

Text #9

Max Range: 3.9274. Min Range: -3.9274

Max Act: 3.0868. Min Act: -0.0000

Data Index: 418895 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 3.9274. Min Range: -3.9274

Max Act: 3.1163. Min Act: -0.0000

Data Index: 705601 (The Pile)

Max Activating Token Index: 675

Text #11

Max Range: 3.9274. Min Range: -3.9274

Max Act: 2.9273. Min Act: -0.0000

Data Index: 703054 (The Pile)

Max Activating Token Index: 229

Text #12

Max Range: 3.9274. Min Range: -3.9274

Max Act: 2.7429. Min Act: -0.0000

Data Index: 251234 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 3.9274. Min Range: -3.9274

Max Act: 2.8728. Min Act: -0.0000

Data Index: 608445 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 3.9274. Min Range: -3.9274

Max Act: 2.8152. Min Act: -0.0000

Data Index: 1534601 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 3.9274. Min Range: -3.9274

Max Act: 2.7946. Min Act: -0.0000

Data Index: 426781 (The Pile)

Max Activating Token Index: 954

Text #16

Max Range: 3.9274. Min Range: -3.9274

Max Act: 2.4761. Min Act: -0.0000

Data Index: 1703797 (The Pile)

Max Activating Token Index: 594

Text #17

Max Range: 3.9274. Min Range: -3.9274

Max Act: 2.5502. Min Act: -0.0000

Data Index: 881986 (The Pile)

Max Activating Token Index: 782

Text #18

Max Range: 3.9274. Min Range: -3.9274

Max Act: 2.6698. Min Act: -0.0000

Data Index: 495055 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 3.9274. Min Range: -3.9274

Max Act: 2.7595. Min Act: -0.0000

Data Index: 328127 (The Pile)

Max Activating Token Index: 649