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

Dataset: The Pile

Neuron 3338 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: 3.5174. Min Range: -3.5174

Max Act: 3.5174. Min Act: -0.0000

Data Index: 693758 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.0919. Min Act: -0.0000

Data Index: 1506559 (The Pile)

Max Activating Token Index: 551

Text #2

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.9867. Min Act: -0.0000

Data Index: 245896 (The Pile)

Max Activating Token Index: 609

Text #3

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.0542. Min Act: -0.0000

Data Index: 1831013 (The Pile)

Max Activating Token Index: 516

Text #4

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.0106. Min Act: -0.0000

Data Index: 205273 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.1051. Min Act: -0.0000

Data Index: 136596 (The Pile)

Max Activating Token Index: 764

Text #6

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.0588. Min Act: -0.0000

Data Index: 758480 (The Pile)

Max Activating Token Index: 368

Text #7

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.8205. Min Act: -0.0000

Data Index: 1118556 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2223. Min Act: -0.0000

Data Index: 1357510 (The Pile)

Max Activating Token Index: 584

Text #9

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2214. Min Act: -0.0000

Data Index: 443997 (The Pile)

Max Activating Token Index: 726

Text #10

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.8842. Min Act: -0.0000

Data Index: 933109 (The Pile)

Max Activating Token Index: 356

Text #11

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.7199. Min Act: -0.0000

Data Index: 1274950 (The Pile)

Max Activating Token Index: 666

Text #12

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.0568. Min Act: -0.0000

Data Index: 1817557 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.8745. Min Act: -0.0000

Data Index: 1366725 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.5290. Min Act: -0.0000

Data Index: 1260313 (The Pile)

Max Activating Token Index: 785

Text #15

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.9086. Min Act: -0.0000

Data Index: 338893 (The Pile)

Max Activating Token Index: 765

Text #16

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.9204. Min Act: -0.0000

Data Index: 635252 (The Pile)

Max Activating Token Index: 418

Text #17

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.6215. Min Act: -0.0000

Data Index: 881814 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.7479. Min Act: -0.0000

Data Index: 917785 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.7427. Min Act: -0.0000

Data Index: 860722 (The Pile)

Max Activating Token Index: 798