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

Dataset: The Pile

Neuron 566 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: 0.7435. Min Range: -0.7435

Max Act: 0.7435. Min Act: -0.0000

Data Index: 1709293 (The Pile)

Max Activating Token Index: 467

Text #1

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6109. Min Act: -0.0000

Data Index: 58228 (The Pile)

Max Activating Token Index: 357

Text #2

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6082. Min Act: -0.0000

Data Index: 359246 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1815977 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5613. Min Act: -0.0000

Data Index: 734138 (The Pile)

Max Activating Token Index: 900

Text #5

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5716. Min Act: -0.0000

Data Index: 853614 (The Pile)

Max Activating Token Index: 774

Text #6

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5602. Min Act: -0.0000

Data Index: 734113 (The Pile)

Max Activating Token Index: 220

Text #7

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5208. Min Act: -0.0000

Data Index: 122900 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5362. Min Act: -0.0000

Data Index: 959136 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5629. Min Act: -0.0000

Data Index: 389066 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4990. Min Act: -0.0000

Data Index: 435622 (The Pile)

Max Activating Token Index: 528

Text #11

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4983. Min Act: -0.0000

Data Index: 300307 (The Pile)

Max Activating Token Index: 1004

Text #12

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5271. Min Act: -0.0000

Data Index: 208835 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5311. Min Act: -0.0000

Data Index: 473175 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5066. Min Act: -0.0000

Data Index: 696683 (The Pile)

Max Activating Token Index: 964

Text #15

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1111336 (The Pile)

Max Activating Token Index: 700

Text #16

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5223. Min Act: -0.0000

Data Index: 763869 (The Pile)

Max Activating Token Index: 286

Text #17

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1376219 (The Pile)

Max Activating Token Index: 992

Text #18

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5131. Min Act: -0.0000

Data Index: 738871 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1743446 (The Pile)

Max Activating Token Index: 328