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

Dataset: The Pile

Neuron 1596 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1915. Min Act: -0.0000

Data Index: 1391823 (The Pile)

Max Activating Token Index: 383

Text #1

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.3065. Min Act: -0.0000

Data Index: 894223 (The Pile)

Max Activating Token Index: 657

Text #2

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1912. Min Act: -0.0000

Data Index: 989449 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1151. Min Act: -0.0000

Data Index: 108924 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.2149. Min Act: -0.0000

Data Index: 1351151 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1195. Min Act: -0.0000

Data Index: 1452663 (The Pile)

Max Activating Token Index: 159

Text #6

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1586884 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0666. Min Act: -0.0000

Data Index: 1033989 (The Pile)

Max Activating Token Index: 844

Text #8

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0795. Min Act: -0.0000

Data Index: 288075 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 1.3065. Min Range: -1.3065

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1438496 (The Pile)

Max Activating Token Index: 537

Text #10

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0259. Min Act: -0.0000

Data Index: 1128804 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0435. Min Act: -0.0000

Data Index: 1641638 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 1.3065. Min Range: -1.3065

Max Act: 0.9797. Min Act: -0.0000

Data Index: 647594 (The Pile)

Max Activating Token Index: 400

Text #13

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1268. Min Act: -0.0000

Data Index: 449926 (The Pile)

Max Activating Token Index: 378

Text #14

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0616. Min Act: -0.0000

Data Index: 185879 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1181. Min Act: -0.0000

Data Index: 1954367 (The Pile)

Max Activating Token Index: 675

Text #16

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1089. Min Act: -0.0000

Data Index: 1026121 (The Pile)

Max Activating Token Index: 608

Text #17

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0098. Min Act: -0.0000

Data Index: 1549060 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0135. Min Act: -0.0000

Data Index: 1127877 (The Pile)

Max Activating Token Index: 113

Text #19

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0320. Min Act: -0.0000

Data Index: 175881 (The Pile)

Max Activating Token Index: 403