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

Dataset: The Pile

Neuron 3176 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9897. Min Range: -7.9897

Max Act: 7.9897. Min Act: -0.0000

Data Index: 1080071 (The Pile)

Max Activating Token Index: 881

Text #1

Max Range: 7.9897. Min Range: -7.9897

Max Act: 7.9292. Min Act: -0.0000

Data Index: 985417 (The Pile)

Max Activating Token Index: 721

Text #2

Max Range: 7.9897. Min Range: -7.9897

Max Act: 7.8641. Min Act: -0.0000

Data Index: 1445002 (The Pile)

Max Activating Token Index: 684

Text #3

Max Range: 7.9897. Min Range: -7.9897

Max Act: 7.6315. Min Act: -0.0000

Data Index: 250031 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 7.9897. Min Range: -7.9897

Max Act: 7.3175. Min Act: -0.0000

Data Index: 895378 (The Pile)

Max Activating Token Index: 669

Text #5

Max Range: 7.9897. Min Range: -7.9897

Max Act: 6.8823. Min Act: -0.0000

Data Index: 1325263 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 7.9897. Min Range: -7.9897

Max Act: 6.8267. Min Act: -0.0000

Data Index: 1285218 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 7.9897. Min Range: -7.9897

Max Act: 7.3038. Min Act: -0.0000

Data Index: 325872 (The Pile)

Max Activating Token Index: 562

Text #8

Max Range: 7.9897. Min Range: -7.9897

Max Act: 6.6169. Min Act: -0.0000

Data Index: 1904683 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 7.9897. Min Range: -7.9897

Max Act: 6.8684. Min Act: -0.0000

Data Index: 485583 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 7.9897. Min Range: -7.9897

Max Act: 6.5787. Min Act: -0.0000

Data Index: 433589 (The Pile)

Max Activating Token Index: 434

Text #11

Max Range: 7.9897. Min Range: -7.9897

Max Act: 6.3294. Min Act: -0.0000

Data Index: 179149 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 7.9897. Min Range: -7.9897

Max Act: 6.5412. Min Act: -0.0000

Data Index: 1017954 (The Pile)

Max Activating Token Index: 592

Text #13

Max Range: 7.9897. Min Range: -7.9897

Max Act: 6.2775. Min Act: -0.0000

Data Index: 883234 (The Pile)

Max Activating Token Index: 852

Text #14

Max Range: 7.9897. Min Range: -7.9897

Max Act: 6.1073. Min Act: -0.0000

Data Index: 1725090 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 7.9897. Min Range: -7.9897

Max Act: 5.9539. Min Act: -0.0000

Data Index: 1756863 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 7.9897. Min Range: -7.9897

Max Act: 5.9801. Min Act: -0.0000

Data Index: 1354000 (The Pile)

Max Activating Token Index: 266

Text #17

Max Range: 7.9897. Min Range: -7.9897

Max Act: 6.0189. Min Act: -0.0000

Data Index: 279500 (The Pile)

Max Activating Token Index: 251

Text #18

Max Range: 7.9897. Min Range: -7.9897

Max Act: 5.9420. Min Act: -0.0000

Data Index: 937464 (The Pile)

Max Activating Token Index: 916

Text #19

Max Range: 7.9897. Min Range: -7.9897

Max Act: 5.9007. Min Act: -0.0000

Data Index: 727535 (The Pile)

Max Activating Token Index: 661