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

Dataset: The Pile

Neuron 979 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: 0.3676. Min Range: -0.3676

Max Act: 0.3676. Min Act: -0.0000

Data Index: 485333 (The Pile)

Max Activating Token Index: 417

Text #1

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3552. Min Act: -0.0000

Data Index: 914843 (The Pile)

Max Activating Token Index: 858

Text #2

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3591. Min Act: -0.0000

Data Index: 674897 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3489. Min Act: -0.0000

Data Index: 529362 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3491. Min Act: 0.0000

Data Index: 1244010 (The Pile)

Max Activating Token Index: 710

Text #5

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3366. Min Act: -0.0000

Data Index: 263230 (The Pile)

Max Activating Token Index: 350

Text #6

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1213434 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3311. Min Act: -0.0000

Data Index: 873825 (The Pile)

Max Activating Token Index: 657

Text #8

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3099. Min Act: -0.0000

Data Index: 208039 (The Pile)

Max Activating Token Index: 476

Text #9

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1399998 (The Pile)

Max Activating Token Index: 649

Text #10

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3057. Min Act: -0.0000

Data Index: 187757 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1632719 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1966872 (The Pile)

Max Activating Token Index: 111

Text #13

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3414. Min Act: -0.0000

Data Index: 370778 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1603190 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1494405 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1340032 (The Pile)

Max Activating Token Index: 867

Text #17

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2940. Min Act: -0.0000

Data Index: 500849 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1119824 (The Pile)

Max Activating Token Index: 637

Text #19

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2918. Min Act: -0.0000

Data Index: 553015 (The Pile)

Max Activating Token Index: 995