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

Dataset: The Pile

Neuron 960 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: 1.1614. Min Range: -1.1614

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1243623 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.0035. Min Act: -0.0000

Data Index: 252125 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9773. Min Act: -0.0000

Data Index: 31066 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.0151. Min Act: -0.0000

Data Index: 547179 (The Pile)

Max Activating Token Index: 555

Text #4

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.8890. Min Act: -0.0000

Data Index: 514342 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1425346 (The Pile)

Max Activating Token Index: 434

Text #6

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1942663 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9286. Min Act: -0.0000

Data Index: 820830 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.8280. Min Act: -0.0000

Data Index: 147825 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1375809 (The Pile)

Max Activating Token Index: 842

Text #10

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.8272. Min Act: -0.0000

Data Index: 248629 (The Pile)

Max Activating Token Index: 977

Text #11

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.8286. Min Act: -0.0000

Data Index: 704129 (The Pile)

Max Activating Token Index: 132

Text #12

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.7850. Min Act: 0.0000

Data Index: 349840 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.8997. Min Act: -0.0000

Data Index: 82737 (The Pile)

Max Activating Token Index: 416

Text #14

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.8141. Min Act: -0.0000

Data Index: 651264 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.7924. Min Act: -0.0000

Data Index: 144244 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1942059 (The Pile)

Max Activating Token Index: 872

Text #17

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1300318 (The Pile)

Max Activating Token Index: 498

Text #18

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1653154 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1053615 (The Pile)

Max Activating Token Index: 888