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

Dataset: The Pile

Neuron 3686 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: 1.4515. Min Range: -1.4515

Max Act: 1.4515. Min Act: -0.0000

Data Index: 367778 (The Pile)

Max Activating Token Index: 453

Text #1

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.2045. Min Act: -0.0000

Data Index: 1911432 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 1.4515. Min Range: -1.4515

Max Act: 1.0347. Min Act: -0.0000

Data Index: 1159861 (The Pile)

Max Activating Token Index: 619

Text #3

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.9712. Min Act: -0.0000

Data Index: 824939 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.9701. Min Act: -0.0000

Data Index: 722488 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.8727. Min Act: -0.0000

Data Index: 475718 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1819353 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1741519 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1449702 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.9410. Min Act: -0.0000

Data Index: 309439 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.8869. Min Act: -0.0000

Data Index: 617098 (The Pile)

Max Activating Token Index: 254

Text #11

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.9098. Min Act: -0.0000

Data Index: 315708 (The Pile)

Max Activating Token Index: 172

Text #12

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1859313 (The Pile)

Max Activating Token Index: 854

Text #13

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.7656. Min Act: -0.0000

Data Index: 131539 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1950962 (The Pile)

Max Activating Token Index: 928

Text #15

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.7991. Min Act: -0.0000

Data Index: 476283 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.8126. Min Act: -0.0000

Data Index: 798847 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.7940. Min Act: -0.0000

Data Index: 546546 (The Pile)

Max Activating Token Index: 692

Text #18

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.7889. Min Act: -0.0000

Data Index: 483032 (The Pile)

Max Activating Token Index: 198

Text #19

Max Range: 1.4515. Min Range: -1.4515

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1133568 (The Pile)

Max Activating Token Index: 833