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

Dataset: The Pile

Neuron 1528 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: 1.1774. Min Range: -1.1774

Max Act: 1.1774. Min Act: -0.0000

Data Index: 749656 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 1.1774. Min Range: -1.1774

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1301741 (The Pile)

Max Activating Token Index: 781

Text #2

Max Range: 1.1774. Min Range: -1.1774

Max Act: 1.0353. Min Act: -0.0000

Data Index: 1881925 (The Pile)

Max Activating Token Index: 977

Text #3

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9902. Min Act: -0.0000

Data Index: 244337 (The Pile)

Max Activating Token Index: 781

Text #4

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9831. Min Act: -0.0000

Data Index: 778330 (The Pile)

Max Activating Token Index: 276

Text #5

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1426227 (The Pile)

Max Activating Token Index: 85

Text #6

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8395. Min Act: -0.0000

Data Index: 911686 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1990673 (The Pile)

Max Activating Token Index: 583

Text #8

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9096. Min Act: -0.0000

Data Index: 935209 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9035. Min Act: -0.0000

Data Index: 1250922 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1108854 (The Pile)

Max Activating Token Index: 161

Text #11

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8686. Min Act: -0.0000

Data Index: 654501 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1695325 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1129289 (The Pile)

Max Activating Token Index: 420

Text #14

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1107946 (The Pile)

Max Activating Token Index: 590

Text #15

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1627760 (The Pile)

Max Activating Token Index: 436

Text #16

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1141133 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8182. Min Act: -0.0000

Data Index: 1647671 (The Pile)

Max Activating Token Index: 162

Text #18

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1390342 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8231. Min Act: -0.0000

Data Index: 951551 (The Pile)

Max Activating Token Index: 45