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

Dataset: The Pile

Neuron 4671 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: 1.3682. Min Range: -1.3682

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1334183 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.2653. Min Act: 0.0000

Data Index: 1560782 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.3268. Min Act: -0.0000

Data Index: 856695 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1494740 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1259. Min Act: -0.0000

Data Index: 1069747 (The Pile)

Max Activating Token Index: 677

Text #5

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1585. Min Act: -0.0000

Data Index: 702658 (The Pile)

Max Activating Token Index: 359

Text #6

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0760. Min Act: -0.0000

Data Index: 1620462 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1377503 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0570. Min Act: -0.0000

Data Index: 740575 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0777. Min Act: -0.0000

Data Index: 1997455 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1107. Min Act: -0.0000

Data Index: 1929446 (The Pile)

Max Activating Token Index: 507

Text #11

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1107. Min Act: -0.0000

Data Index: 1902013 (The Pile)

Max Activating Token Index: 204

Text #12

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1067720 (The Pile)

Max Activating Token Index: 443

Text #13

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1990871 (The Pile)

Max Activating Token Index: 578

Text #14

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0706. Min Act: -0.0000

Data Index: 967274 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0261. Min Act: -0.0000

Data Index: 1181881 (The Pile)

Max Activating Token Index: 249

Text #16

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0576. Min Act: 0.0000

Data Index: 1540183 (The Pile)

Max Activating Token Index: 467

Text #17

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1825030 (The Pile)

Max Activating Token Index: 48

Text #18

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1521922 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0247. Min Act: -0.0000

Data Index: 250964 (The Pile)

Max Activating Token Index: 44