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

Dataset: The Pile

Neuron 3276 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: 0.2168. Min Range: -0.2168

Max Act: 0.2168. Min Act: -0.0000

Data Index: 238731 (The Pile)

Max Activating Token Index: 513

Text #1

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1607. Min Act: -0.0000

Data Index: 676509 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1145237 (The Pile)

Max Activating Token Index: 950

Text #3

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1887882 (The Pile)

Max Activating Token Index: 845

Text #4

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1538. Min Act: -0.0000

Data Index: 421069 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1540. Min Act: -0.0000

Data Index: 359651 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1070563 (The Pile)

Max Activating Token Index: 817

Text #7

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1426. Min Act: -0.0000

Data Index: 634829 (The Pile)

Max Activating Token Index: 167

Text #8

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1011710 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1430817 (The Pile)

Max Activating Token Index: 184

Text #10

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1528. Min Act: -0.0000

Data Index: 207442 (The Pile)

Max Activating Token Index: 148

Text #11

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1478. Min Act: -0.0000

Data Index: 1057312 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1212340 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1338. Min Act: -0.0000

Data Index: 562269 (The Pile)

Max Activating Token Index: 744

Text #14

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1259. Min Act: -0.0000

Data Index: 224690 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1272. Min Act: -0.0000

Data Index: 894259 (The Pile)

Max Activating Token Index: 917

Text #16

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1259. Min Act: -0.0000

Data Index: 989726 (The Pile)

Max Activating Token Index: 636

Text #17

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1259. Min Act: -0.0000

Data Index: 624597 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1246. Min Act: -0.0000

Data Index: 905017 (The Pile)

Max Activating Token Index: 185

Text #19

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1251. Min Act: -0.0000

Data Index: 754038 (The Pile)

Max Activating Token Index: 234