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

Dataset: The Pile

Neuron 2517 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: 1.6220. Min Range: -1.6220

Max Act: 1.6220. Min Act: -0.0000

Data Index: 1814397 (The Pile)

Max Activating Token Index: 78

Text #1

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.4915. Min Act: -0.0000

Data Index: 71037 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.5484. Min Act: -0.0000

Data Index: 839177 (The Pile)

Max Activating Token Index: 957

Text #3

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.4310. Min Act: -0.0000

Data Index: 102113 (The Pile)

Max Activating Token Index: 993

Text #4

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3965. Min Act: -0.0000

Data Index: 153622 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3349. Min Act: -0.0000

Data Index: 993117 (The Pile)

Max Activating Token Index: 955

Text #6

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2372. Min Act: -0.0000

Data Index: 18872 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3559. Min Act: -0.0000

Data Index: 281280 (The Pile)

Max Activating Token Index: 709

Text #8

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3206. Min Act: -0.0000

Data Index: 1875404 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3992. Min Act: -0.0000

Data Index: 172352 (The Pile)

Max Activating Token Index: 745

Text #10

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2592. Min Act: -0.0000

Data Index: 808058 (The Pile)

Max Activating Token Index: 844

Text #11

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2197. Min Act: -0.0000

Data Index: 509345 (The Pile)

Max Activating Token Index: 735

Text #12

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3147. Min Act: -0.0000

Data Index: 1327325 (The Pile)

Max Activating Token Index: 827

Text #13

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3381. Min Act: -0.0000

Data Index: 1055645 (The Pile)

Max Activating Token Index: 823

Text #14

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.1806. Min Act: -0.0000

Data Index: 609372 (The Pile)

Max Activating Token Index: 789

Text #15

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2860. Min Act: -0.0000

Data Index: 1867335 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.1957. Min Act: -0.0000

Data Index: 660815 (The Pile)

Max Activating Token Index: 959

Text #17

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2765. Min Act: -0.0000

Data Index: 1503108 (The Pile)

Max Activating Token Index: 958

Text #18

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3076. Min Act: -0.0000

Data Index: 1748268 (The Pile)

Max Activating Token Index: 739

Text #19

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3670. Min Act: -0.0000

Data Index: 975836 (The Pile)

Max Activating Token Index: 887