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

Dataset: The Pile

Neuron 3215 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: 3.1290. Min Range: -3.1290

Max Act: 3.1290. Min Act: -0.0000

Data Index: 329681 (The Pile)

Max Activating Token Index: 320

Text #1

Max Range: 3.1290. Min Range: -3.1290

Max Act: 3.0553. Min Act: -0.0000

Data Index: 1744321 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.8612. Min Act: -0.0000

Data Index: 1243170 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.9233. Min Act: -0.0000

Data Index: 421216 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.5239. Min Act: -0.0000

Data Index: 1462462 (The Pile)

Max Activating Token Index: 526

Text #5

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.5137. Min Act: -0.0000

Data Index: 615640 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.4888. Min Act: -0.0000

Data Index: 1681738 (The Pile)

Max Activating Token Index: 105

Text #7

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.7304. Min Act: -0.0000

Data Index: 396660 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.3084. Min Act: -0.0000

Data Index: 1434158 (The Pile)

Max Activating Token Index: 580

Text #9

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.4188. Min Act: -0.0000

Data Index: 309205 (The Pile)

Max Activating Token Index: 702

Text #10

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.2966. Min Act: -0.0000

Data Index: 830463 (The Pile)

Max Activating Token Index: 864

Text #11

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.1714. Min Act: -0.0000

Data Index: 1684702 (The Pile)

Max Activating Token Index: 569

Text #12

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.0888. Min Act: -0.0000

Data Index: 1332378 (The Pile)

Max Activating Token Index: 520

Text #13

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.5571. Min Act: -0.0000

Data Index: 1120184 (The Pile)

Max Activating Token Index: 191

Text #14

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.3654. Min Act: -0.0000

Data Index: 1706671 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.1974. Min Act: -0.0000

Data Index: 1600876 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.1552. Min Act: -0.0000

Data Index: 1310996 (The Pile)

Max Activating Token Index: 708

Text #17

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.1490. Min Act: -0.0000

Data Index: 566140 (The Pile)

Max Activating Token Index: 606

Text #18

Max Range: 3.1290. Min Range: -3.1290

Max Act: 1.8979. Min Act: -0.0000

Data Index: 1117640 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.1112. Min Act: -0.0000

Data Index: 1143205 (The Pile)

Max Activating Token Index: 658