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

Dataset: The Pile

Neuron 3341 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: 3.1284. Min Range: -3.1284

Max Act: 3.0337. Min Act: -0.0000

Data Index: 1237987 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.1284. Min Act: -0.0000

Data Index: 1947560 (The Pile)

Max Activating Token Index: 507

Text #2

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.8503. Min Act: -0.0000

Data Index: 1314817 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.8040. Min Act: -0.0000

Data Index: 273797 (The Pile)

Max Activating Token Index: 421

Text #4

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.7667. Min Act: -0.0000

Data Index: 667071 (The Pile)

Max Activating Token Index: 164

Text #5

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.8629. Min Act: -0.0000

Data Index: 1977947 (The Pile)

Max Activating Token Index: 537

Text #6

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.7286. Min Act: -0.0000

Data Index: 1988279 (The Pile)

Max Activating Token Index: 510

Text #7

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.8334. Min Act: -0.0000

Data Index: 1615743 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.6607. Min Act: -0.0000

Data Index: 336392 (The Pile)

Max Activating Token Index: 1018

Text #9

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.5694. Min Act: -0.0000

Data Index: 922918 (The Pile)

Max Activating Token Index: 866

Text #10

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.5308. Min Act: -0.0000

Data Index: 985123 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.5033. Min Act: -0.0000

Data Index: 1815881 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.6254. Min Act: -0.0000

Data Index: 1953567 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.6384. Min Act: -0.0000

Data Index: 258782 (The Pile)

Max Activating Token Index: 942

Text #14

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.3708. Min Act: -0.0000

Data Index: 564539 (The Pile)

Max Activating Token Index: 778

Text #15

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.3742. Min Act: -0.0000

Data Index: 1549564 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.5020. Min Act: -0.0000

Data Index: 1660798 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.4813. Min Act: -0.0000

Data Index: 254521 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.4855. Min Act: -0.0000

Data Index: 680329 (The Pile)

Max Activating Token Index: 854

Text #19

Max Range: 3.1284. Min Range: -3.1284

Max Act: 2.4861. Min Act: -0.0000

Data Index: 919632 (The Pile)

Max Activating Token Index: 571