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

Dataset: The Pile

Neuron 3596 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.6168. Min Act: -0.0000

Data Index: 458408 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.1314. Min Act: -0.0000

Data Index: 1345406 (The Pile)

Max Activating Token Index: 717

Text #2

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.2254. Min Act: -0.0000

Data Index: 1949086 (The Pile)

Max Activating Token Index: 732

Text #3

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9986. Min Act: -0.0000

Data Index: 99539 (The Pile)

Max Activating Token Index: 252

Text #4

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9402. Min Act: -0.0000

Data Index: 336178 (The Pile)

Max Activating Token Index: 320

Text #5

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0062. Min Act: -0.0000

Data Index: 299499 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9887. Min Act: -0.0000

Data Index: 259647 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9777. Min Act: -0.0000

Data Index: 925755 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1347506 (The Pile)

Max Activating Token Index: 414

Text #9

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9186. Min Act: -0.0000

Data Index: 1509009 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1684348 (The Pile)

Max Activating Token Index: 175

Text #11

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.7425. Min Act: -0.0000

Data Index: 855604 (The Pile)

Max Activating Token Index: 881

Text #12

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.8854. Min Act: -0.0000

Data Index: 927476 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.7829. Min Act: -0.0000

Data Index: 724053 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1601348 (The Pile)

Max Activating Token Index: 192

Text #15

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.7828. Min Act: -0.0000

Data Index: 744847 (The Pile)

Max Activating Token Index: 782

Text #16

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1752190 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.7651. Min Act: -0.0000

Data Index: 459089 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1641775 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1812456 (The Pile)

Max Activating Token Index: 789