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

Dataset: The Pile

Neuron 1167 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: 0.8624. Min Range: -0.8624

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1799848 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1488268 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.8283. Min Act: -0.0000

Data Index: 197543 (The Pile)

Max Activating Token Index: 149

Text #3

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1123762 (The Pile)

Max Activating Token Index: 841

Text #4

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6738. Min Act: -0.0000

Data Index: 607540 (The Pile)

Max Activating Token Index: 336

Text #5

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6927. Min Act: -0.0000

Data Index: 900496 (The Pile)

Max Activating Token Index: 693

Text #6

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6449. Min Act: -0.0000

Data Index: 441140 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1324443 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5727. Min Act: -0.0000

Data Index: 173195 (The Pile)

Max Activating Token Index: 628

Text #9

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1865760 (The Pile)

Max Activating Token Index: 322

Text #10

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5600. Min Act: -0.0000

Data Index: 829081 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5809. Min Act: -0.0000

Data Index: 367748 (The Pile)

Max Activating Token Index: 481

Text #12

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5615. Min Act: -0.0000

Data Index: 805340 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5288. Min Act: -0.0000

Data Index: 163195 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1283800 (The Pile)

Max Activating Token Index: 963

Text #15

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1129435 (The Pile)

Max Activating Token Index: 173

Text #16

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5330. Min Act: -0.0000

Data Index: 64858 (The Pile)

Max Activating Token Index: 958

Text #17

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1356825 (The Pile)

Max Activating Token Index: 632

Text #18

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5155. Min Act: -0.0000

Data Index: 62783 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5019. Min Act: -0.0000

Data Index: 138608 (The Pile)

Max Activating Token Index: 877