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

Dataset: The Pile

Neuron 352 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: 1.5675. Min Range: -1.5675

Max Act: 1.4339. Min Act: -0.0000

Data Index: 229739 (The Pile)

Max Activating Token Index: 282

Text #1

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5675. Min Act: -0.0000

Data Index: 307200 (The Pile)

Max Activating Token Index: 677

Text #2

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.4483. Min Act: -0.0000

Data Index: 1543709 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.4402. Min Act: -0.0000

Data Index: 965753 (The Pile)

Max Activating Token Index: 868

Text #4

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.2412. Min Act: -0.0000

Data Index: 1387745 (The Pile)

Max Activating Token Index: 941

Text #5

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.2121. Min Act: -0.0000

Data Index: 386260 (The Pile)

Max Activating Token Index: 207

Text #6

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.2385. Min Act: -0.0000

Data Index: 1368118 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.1782. Min Act: -0.0000

Data Index: 122501 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.2038. Min Act: -0.0000

Data Index: 642715 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.1771. Min Act: -0.0000

Data Index: 744059 (The Pile)

Max Activating Token Index: 423

Text #10

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1197618 (The Pile)

Max Activating Token Index: 772

Text #11

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.1454. Min Act: -0.0000

Data Index: 68600 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.1066. Min Act: -0.0000

Data Index: 468364 (The Pile)

Max Activating Token Index: 362

Text #13

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.0389. Min Act: -0.0000

Data Index: 1787035 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.0990. Min Act: -0.0000

Data Index: 907341 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1194770 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1306615 (The Pile)

Max Activating Token Index: 121

Text #17

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1448959 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.1176. Min Act: -0.0000

Data Index: 398598 (The Pile)

Max Activating Token Index: 320

Text #19

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.0439. Min Act: -0.0000

Data Index: 1911292 (The Pile)

Max Activating Token Index: 187