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

Dataset: The Pile

Neuron 1604 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: 0.1667. Min Range: -0.1667

Max Act: 0.1667. Min Act: -0.0000

Data Index: 60137 (The Pile)

Max Activating Token Index: 524

Text #1

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1533. Min Act: -0.0000

Data Index: 618324 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1405883 (The Pile)

Max Activating Token Index: 813

Text #3

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1297. Min Act: -0.0000

Data Index: 495791 (The Pile)

Max Activating Token Index: 728

Text #4

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1410552 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1698212 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1490. Min Act: -0.0000

Data Index: 186551 (The Pile)

Max Activating Token Index: 731

Text #7

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1435529 (The Pile)

Max Activating Token Index: 502

Text #8

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1503. Min Act: -0.0000

Data Index: 830936 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1513389 (The Pile)

Max Activating Token Index: 387

Text #10

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1482698 (The Pile)

Max Activating Token Index: 115

Text #11

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1403. Min Act: -0.0000

Data Index: 918990 (The Pile)

Max Activating Token Index: 647

Text #12

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1366. Min Act: -0.0000

Data Index: 1305954 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1314. Min Act: -0.0000

Data Index: 686385 (The Pile)

Max Activating Token Index: 518

Text #14

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1472885 (The Pile)

Max Activating Token Index: 601

Text #15

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1043127 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1292. Min Act: -0.0000

Data Index: 587994 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1138. Min Act: -0.0000

Data Index: 281861 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1204. Min Act: -0.0000

Data Index: 80579 (The Pile)

Max Activating Token Index: 619

Text #19

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1472528 (The Pile)

Max Activating Token Index: 387