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

Dataset: The Pile

Neuron 229 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.8220. Min Act: -0.0000

Data Index: 490989 (The Pile)

Max Activating Token Index: 332

Text #1

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6686. Min Act: -0.0000

Data Index: 969237 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1899460 (The Pile)

Max Activating Token Index: 825

Text #3

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.5883. Min Act: -0.0000

Data Index: 787829 (The Pile)

Max Activating Token Index: 9

Text #4

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6362. Min Act: -0.0000

Data Index: 961974 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1541560 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6344. Min Act: -0.0000

Data Index: 822364 (The Pile)

Max Activating Token Index: 691

Text #7

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1636819 (The Pile)

Max Activating Token Index: 630

Text #8

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6288. Min Act: -0.0000

Data Index: 757791 (The Pile)

Max Activating Token Index: 889

Text #9

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.5744. Min Act: -0.0000

Data Index: 868717 (The Pile)

Max Activating Token Index: 718

Text #10

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.5955. Min Act: -0.0000

Data Index: 878890 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1250499 (The Pile)

Max Activating Token Index: 283

Text #12

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.5504. Min Act: -0.0000

Data Index: 792618 (The Pile)

Max Activating Token Index: 776

Text #13

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1951633 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.5910. Min Act: -0.0000

Data Index: 999495 (The Pile)

Max Activating Token Index: 820

Text #15

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1964366 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.5854. Min Act: -0.0000

Data Index: 762199 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.5954. Min Act: -0.0000

Data Index: 585018 (The Pile)

Max Activating Token Index: 156

Text #18

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1684401 (The Pile)

Max Activating Token Index: 140

Text #19

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.5735. Min Act: -0.0000

Data Index: 1534702 (The Pile)

Max Activating Token Index: 308