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

Dataset: The Pile

Neuron 1485 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: 2.6379. Min Range: -2.6379

Max Act: 2.6379. Min Act: -0.0000

Data Index: 1918631 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.5143. Min Act: -0.0000

Data Index: 183219 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.4553. Min Act: -0.0000

Data Index: 1458926 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.2754. Min Act: -0.0000

Data Index: 1271768 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.3901. Min Act: -0.0000

Data Index: 936015 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.3529. Min Act: -0.0000

Data Index: 1905329 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.2467. Min Act: -0.0000

Data Index: 455058 (The Pile)

Max Activating Token Index: 274

Text #7

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.1040. Min Act: -0.0000

Data Index: 1391161 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.1397. Min Act: -0.0000

Data Index: 297699 (The Pile)

Max Activating Token Index: 765

Text #9

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.1322. Min Act: -0.0000

Data Index: 1362631 (The Pile)

Max Activating Token Index: 940

Text #10

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.2598. Min Act: -0.0000

Data Index: 92580 (The Pile)

Max Activating Token Index: 78

Text #11

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.0887. Min Act: -0.0000

Data Index: 1168834 (The Pile)

Max Activating Token Index: 913

Text #12

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.2032. Min Act: -0.0000

Data Index: 1077000 (The Pile)

Max Activating Token Index: 90

Text #13

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.0862. Min Act: -0.0000

Data Index: 1611177 (The Pile)

Max Activating Token Index: 789

Text #14

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.0920. Min Act: -0.0000

Data Index: 470699 (The Pile)

Max Activating Token Index: 856

Text #15

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.0693. Min Act: -0.0000

Data Index: 17008 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 2.6379. Min Range: -2.6379

Max Act: 1.9577. Min Act: -0.0000

Data Index: 1353799 (The Pile)

Max Activating Token Index: 532

Text #17

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.0508. Min Act: -0.0000

Data Index: 1378797 (The Pile)

Max Activating Token Index: 307

Text #18

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.0173. Min Act: -0.0000

Data Index: 1002255 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 2.6379. Min Range: -2.6379

Max Act: 1.9172. Min Act: -0.0000

Data Index: 1975618 (The Pile)

Max Activating Token Index: 691