Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 716 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8050. Min Act: -0.0000

Data Index: 539628 (The Pile)

Max Activating Token Index: 427

Text #1

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.7931. Min Act: -0.0000

Data Index: 674447 (The Pile)

Max Activating Token Index: 933

Text #2

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.9281. Min Act: -0.0000

Data Index: 1082186 (The Pile)

Max Activating Token Index: 682

Text #3

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.6926. Min Act: -0.0000

Data Index: 1160406 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.7291. Min Act: -0.0000

Data Index: 527501 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.4354. Min Act: -0.0000

Data Index: 1498364 (The Pile)

Max Activating Token Index: 804

Text #6

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.6678. Min Act: -0.0000

Data Index: 540111 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.6294. Min Act: -0.0000

Data Index: 131999 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.6275. Min Act: -0.0000

Data Index: 1947872 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.5292. Min Act: -0.0000

Data Index: 1024456 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.5308. Min Act: -0.0000

Data Index: 1677238 (The Pile)

Max Activating Token Index: 260

Text #11

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.6163. Min Act: -0.0000

Data Index: 1962119 (The Pile)

Max Activating Token Index: 437

Text #12

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.6139. Min Act: -0.0000

Data Index: 1435626 (The Pile)

Max Activating Token Index: 592

Text #13

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.4983. Min Act: -0.0000

Data Index: 1033834 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.5676. Min Act: -0.0000

Data Index: 1298293 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.3904. Min Act: -0.0000

Data Index: 693924 (The Pile)

Max Activating Token Index: 995

Text #16

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.5563. Min Act: -0.0000

Data Index: 952875 (The Pile)

Max Activating Token Index: 418

Text #17

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.5452. Min Act: -0.0000

Data Index: 1750187 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.5235. Min Act: -0.0000

Data Index: 1823011 (The Pile)

Max Activating Token Index: 527

Text #19

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.4391. Min Act: -0.0000

Data Index: 115929 (The Pile)

Max Activating Token Index: 287