Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 372 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.9200. Min Act: -0.0000

Data Index: 1014863 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.4861. Min Act: -0.0000

Data Index: 403904 (The Pile)

Max Activating Token Index: 636

Text #2

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.6484. Min Act: -0.0000

Data Index: 1377732 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.5011. Min Act: -0.0000

Data Index: 1354801 (The Pile)

Max Activating Token Index: 938

Text #4

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.5504. Min Act: -0.0000

Data Index: 45159 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.2763. Min Act: -0.0000

Data Index: 181583 (The Pile)

Max Activating Token Index: 486

Text #6

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.5067. Min Act: -0.0000

Data Index: 1614257 (The Pile)

Max Activating Token Index: 480

Text #7

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.4553. Min Act: -0.0000

Data Index: 1788899 (The Pile)

Max Activating Token Index: 163

Text #8

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.3431. Min Act: -0.0000

Data Index: 864224 (The Pile)

Max Activating Token Index: 690

Text #9

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1028624 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.2370. Min Act: -0.0000

Data Index: 1812390 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.2259. Min Act: -0.0000

Data Index: 996504 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.2952. Min Act: -0.0000

Data Index: 806487 (The Pile)

Max Activating Token Index: 677

Text #13

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.1609. Min Act: -0.0000

Data Index: 317957 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.1524. Min Act: -0.0000

Data Index: 1869941 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.2814. Min Act: -0.0001

Data Index: 19359 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.0180. Min Act: -0.0000

Data Index: 1374764 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.1399. Min Act: -0.0000

Data Index: 493881 (The Pile)

Max Activating Token Index: 932

Text #18

Max Range: 1.9200. Min Range: -1.9200

Max Act: 0.9489. Min Act: -0.0000

Data Index: 1105905 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 1.9200. Min Range: -1.9200

Max Act: 0.8396. Min Act: -0.0000

Data Index: 1987026 (The Pile)

Max Activating Token Index: 721