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

Dataset: The Pile

Neuron 1702 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: 0.9365. Min Range: -0.9365

Max Act: 0.8973. Min Act: -0.0000

Data Index: 724493 (The Pile)

Max Activating Token Index: 966

Text #1

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9365. Min Act: -0.0000

Data Index: 57608 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1321563 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9044. Min Act: -0.0000

Data Index: 14194 (The Pile)

Max Activating Token Index: 717

Text #4

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8850. Min Act: -0.0000

Data Index: 968992 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1201752 (The Pile)

Max Activating Token Index: 778

Text #6

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1041131 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1430564 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9040. Min Act: -0.0000

Data Index: 135466 (The Pile)

Max Activating Token Index: 595

Text #9

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1420701 (The Pile)

Max Activating Token Index: 291

Text #10

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8118. Min Act: -0.0000

Data Index: 401205 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1672379 (The Pile)

Max Activating Token Index: 383

Text #12

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1779914 (The Pile)

Max Activating Token Index: 144

Text #13

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1122334 (The Pile)

Max Activating Token Index: 1018

Text #14

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8464. Min Act: -0.0000

Data Index: 1300699 (The Pile)

Max Activating Token Index: 544

Text #15

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7780. Min Act: -0.0000

Data Index: 553693 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8034. Min Act: -0.0000

Data Index: 245775 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1388576 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8405. Min Act: -0.0000

Data Index: 273559 (The Pile)

Max Activating Token Index: 416

Text #19

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8436. Min Act: -0.0000

Data Index: 726816 (The Pile)

Max Activating Token Index: 370