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

Dataset: The Pile

Neuron 2295 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.3400. Min Act: -0.0000

Data Index: 1749446 (The Pile)

Max Activating Token Index: 508

Text #1

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.3256. Min Act: -0.0000

Data Index: 604031 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9597. Min Act: -0.0000

Data Index: 1046925 (The Pile)

Max Activating Token Index: 458

Text #3

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.0726. Min Act: -0.0000

Data Index: 647781 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9389. Min Act: -0.0000

Data Index: 1962234 (The Pile)

Max Activating Token Index: 552

Text #5

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9396. Min Act: -0.0000

Data Index: 1103517 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.0351. Min Act: -0.0000

Data Index: 1444852 (The Pile)

Max Activating Token Index: 724

Text #7

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.1693. Min Act: -0.0000

Data Index: 1349715 (The Pile)

Max Activating Token Index: 790

Text #8

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9781. Min Act: -0.0000

Data Index: 1806483 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9964. Min Act: -0.0000

Data Index: 953001 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9424. Min Act: -0.0000

Data Index: 1493118 (The Pile)

Max Activating Token Index: 613

Text #11

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.8121. Min Act: -0.0000

Data Index: 301114 (The Pile)

Max Activating Token Index: 517

Text #12

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.0640. Min Act: -0.0001

Data Index: 368954 (The Pile)

Max Activating Token Index: 867

Text #13

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.8002. Min Act: -0.0000

Data Index: 1169805 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9345. Min Act: -0.0000

Data Index: 414687 (The Pile)

Max Activating Token Index: 533

Text #15

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9024. Min Act: -0.0001

Data Index: 484004 (The Pile)

Max Activating Token Index: 744

Text #16

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9122. Min Act: -0.0000

Data Index: 336080 (The Pile)

Max Activating Token Index: 435

Text #17

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9221. Min Act: -0.0000

Data Index: 326848 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.7221. Min Act: -0.0000

Data Index: 1815315 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.8404. Min Act: -0.0000

Data Index: 588505 (The Pile)

Max Activating Token Index: 1019