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

Dataset: The Pile

Neuron 3601 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1080515 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1968852 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.5390. Min Act: -0.0000

Data Index: 19803 (The Pile)

Max Activating Token Index: 509

Text #3

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.5218. Min Act: -0.0000

Data Index: 230796 (The Pile)

Max Activating Token Index: 996

Text #4

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.5614. Min Act: -0.0000

Data Index: 504790 (The Pile)

Max Activating Token Index: 1016

Text #5

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.5061. Min Act: 0.0000

Data Index: 503328 (The Pile)

Max Activating Token Index: 859

Text #6

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1061456 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1484325 (The Pile)

Max Activating Token Index: 787

Text #8

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4566. Min Act: 0.0000

Data Index: 307624 (The Pile)

Max Activating Token Index: 716

Text #9

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1270774 (The Pile)

Max Activating Token Index: 999

Text #10

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4411. Min Act: -0.0000

Data Index: 116586 (The Pile)

Max Activating Token Index: 650

Text #11

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.5039. Min Act: 0.0000

Data Index: 888589 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1688573 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1178882 (The Pile)

Max Activating Token Index: 306

Text #14

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4491. Min Act: 0.0000

Data Index: 1023142 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4471. Min Act: 0.0000

Data Index: 1210708 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1675620 (The Pile)

Max Activating Token Index: 819

Text #17

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1648869 (The Pile)

Max Activating Token Index: 198

Text #18

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4489. Min Act: -0.0000

Data Index: 325438 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4354. Min Act: -0.0000

Data Index: 119290 (The Pile)

Max Activating Token Index: 366