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

Dataset: The Pile

Neuron 1954 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1210112 (The Pile)

Max Activating Token Index: 820

Text #1

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1591. Min Act: -0.0000

Data Index: 910163 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1514. Min Act: 0.0000

Data Index: 599876 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1764718 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1511668 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1174385 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1342. Min Act: -0.0000

Data Index: 120184 (The Pile)

Max Activating Token Index: 329

Text #7

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1442. Min Act: -0.0000

Data Index: 376020 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1382. Min Act: -0.0000

Data Index: 863831 (The Pile)

Max Activating Token Index: 298

Text #9

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1370098 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1560894 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1046534 (The Pile)

Max Activating Token Index: 92

Text #12

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1363. Min Act: 0.0000

Data Index: 1572834 (The Pile)

Max Activating Token Index: 364

Text #13

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1365. Min Act: -0.0000

Data Index: 338710 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1318. Min Act: -0.0000

Data Index: 50499 (The Pile)

Max Activating Token Index: 632

Text #15

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1291. Min Act: -0.0000

Data Index: 992393 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1389. Min Act: -0.0000

Data Index: 452199 (The Pile)

Max Activating Token Index: 913

Text #17

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1289. Min Act: -0.0000

Data Index: 76859 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1331. Min Act: -0.0000

Data Index: 1519456 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1412536 (The Pile)

Max Activating Token Index: 400