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

Dataset: The Pile

Neuron 3581 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.4395. Min Act: -0.0000

Data Index: 83075 (The Pile)

Max Activating Token Index: 140

Text #1

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1207173 (The Pile)

Max Activating Token Index: 922

Text #2

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.4470. Min Act: -0.0000

Data Index: 119716 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.4186. Min Act: -0.0000

Data Index: 944689 (The Pile)

Max Activating Token Index: 412

Text #4

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1219011 (The Pile)

Max Activating Token Index: 99

Text #5

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3928. Min Act: -0.0000

Data Index: 515241 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1450573 (The Pile)

Max Activating Token Index: 495

Text #7

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3265. Min Act: 0.0002

Data Index: 212350 (The Pile)

Max Activating Token Index: 887

Text #8

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3109. Min Act: 0.0001

Data Index: 497764 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1663839 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2829. Min Act: -0.0000

Data Index: 629062 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1201813 (The Pile)

Max Activating Token Index: 937

Text #12

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3292. Min Act: -0.0000

Data Index: 802003 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1317858 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1281779 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1166933 (The Pile)

Max Activating Token Index: 854

Text #16

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1609947 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3203. Min Act: -0.0000

Data Index: 163086 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3202. Min Act: -0.0000

Data Index: 57580 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1781487 (The Pile)

Max Activating Token Index: 841