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

Dataset: The Pile

Neuron 1777 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.2487. Min Range: -3.2487

Max Act: 3.2487. Min Act: -0.0000

Data Index: 15657 (The Pile)

Max Activating Token Index: 229

Text #1

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.8767. Min Act: -0.0000

Data Index: 1344374 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.5126. Min Act: -0.0000

Data Index: 1540467 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.1313. Min Act: -0.0000

Data Index: 794408 (The Pile)

Max Activating Token Index: 856

Text #4

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.4279. Min Act: -0.0000

Data Index: 609781 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.3576. Min Act: -0.0000

Data Index: 1767251 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.3356. Min Act: -0.0000

Data Index: 992793 (The Pile)

Max Activating Token Index: 423

Text #7

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.3795. Min Act: -0.0000

Data Index: 1590574 (The Pile)

Max Activating Token Index: 464

Text #8

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.3978. Min Act: -0.0000

Data Index: 1220741 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.1275. Min Act: -0.0000

Data Index: 1149291 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.2505. Min Act: -0.0000

Data Index: 1313760 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.2470. Min Act: -0.0000

Data Index: 1352128 (The Pile)

Max Activating Token Index: 88

Text #12

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.2351. Min Act: -0.0000

Data Index: 954490 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.1283. Min Act: -0.0000

Data Index: 643150 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 3.2487. Min Range: -3.2487

Max Act: 1.9836. Min Act: -0.0000

Data Index: 750866 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 3.2487. Min Range: -3.2487

Max Act: 1.9788. Min Act: -0.0000

Data Index: 1429294 (The Pile)

Max Activating Token Index: 407

Text #16

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.0187. Min Act: -0.0000

Data Index: 1492108 (The Pile)

Max Activating Token Index: 15

Text #17

Max Range: 3.2487. Min Range: -3.2487

Max Act: 2.0150. Min Act: -0.0000

Data Index: 430455 (The Pile)

Max Activating Token Index: 357

Text #18

Max Range: 3.2487. Min Range: -3.2487

Max Act: 1.9766. Min Act: -0.0000

Data Index: 866797 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 3.2487. Min Range: -3.2487

Max Act: 1.9730. Min Act: -0.0000

Data Index: 566393 (The Pile)

Max Activating Token Index: 732