Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 640 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3708. Min Act: -0.0000

Data Index: 94136 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3482. Min Act: -0.0000

Data Index: 807140 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2681. Min Act: -0.0000

Data Index: 962748 (The Pile)

Max Activating Token Index: 478

Text #3

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1721447 (The Pile)

Max Activating Token Index: 690

Text #4

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1165011 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2413. Min Act: -0.0000

Data Index: 653400 (The Pile)

Max Activating Token Index: 963

Text #6

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2341. Min Act: -0.0000

Data Index: 373614 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1796559 (The Pile)

Max Activating Token Index: 863

Text #8

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1454972 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2187. Min Act: -0.0000

Data Index: 67711 (The Pile)

Max Activating Token Index: 607

Text #10

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1106383 (The Pile)

Max Activating Token Index: 484

Text #11

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2238. Min Act: -0.0000

Data Index: 611209 (The Pile)

Max Activating Token Index: 931

Text #12

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1883314 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1233785 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1157797 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1817926 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1648487 (The Pile)

Max Activating Token Index: 986

Text #17

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1352953 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2229. Min Act: -0.0000

Data Index: 96135 (The Pile)

Max Activating Token Index: 769

Text #19

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2106. Min Act: -0.0000

Data Index: 355386 (The Pile)

Max Activating Token Index: 902