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

Dataset: The Pile

Neuron 3586 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: 0.6266. Min Range: -0.6266

Max Act: 0.6266. Min Act: -0.0000

Data Index: 725088 (The Pile)

Max Activating Token Index: 533

Text #1

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.5419. Min Act: -0.0000

Data Index: 782007 (The Pile)

Max Activating Token Index: 363

Text #2

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.5060. Min Act: -0.0000

Data Index: 410810 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.5132. Min Act: -0.0000

Data Index: 293745 (The Pile)

Max Activating Token Index: 567

Text #4

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1943377 (The Pile)

Max Activating Token Index: 79

Text #5

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.5186. Min Act: -0.0000

Data Index: 154965 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1963753 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1548655 (The Pile)

Max Activating Token Index: 315

Text #8

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.5335. Min Act: -0.0000

Data Index: 462106 (The Pile)

Max Activating Token Index: 839

Text #9

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1684284 (The Pile)

Max Activating Token Index: 799

Text #10

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4853. Min Act: -0.0000

Data Index: 601208 (The Pile)

Max Activating Token Index: 85

Text #11

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1684743 (The Pile)

Max Activating Token Index: 330

Text #12

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1729235 (The Pile)

Max Activating Token Index: 570

Text #13

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1518036 (The Pile)

Max Activating Token Index: 682

Text #14

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4857. Min Act: -0.0000

Data Index: 205244 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4711. Min Act: -0.0000

Data Index: 556046 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1803350 (The Pile)

Max Activating Token Index: 392

Text #17

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4686. Min Act: -0.0000

Data Index: 983268 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1552653 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1770618 (The Pile)

Max Activating Token Index: 439