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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4371 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7775. Min Range: -5.7775

Max Act: 5.7775. Min Act: -0.0000

Data Index: 884824 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 5.7775. Min Range: -5.7775

Max Act: 4.9143. Min Act: -0.0000

Data Index: 1277554 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 5.7775. Min Range: -5.7775

Max Act: 4.8098. Min Act: -0.0000

Data Index: 995274 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 5.7775. Min Range: -5.7775

Max Act: 4.6996. Min Act: -0.0000

Data Index: 38375 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 5.7775. Min Range: -5.7775

Max Act: 4.6439. Min Act: -0.0000

Data Index: 1298682 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 5.7775. Min Range: -5.7775

Max Act: 4.5733. Min Act: -0.0000

Data Index: 859893 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 5.7775. Min Range: -5.7775

Max Act: 4.3589. Min Act: -0.0000

Data Index: 952683 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 5.7775. Min Range: -5.7775

Max Act: 4.3686. Min Act: -0.0000

Data Index: 114405 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 5.7775. Min Range: -5.7775

Max Act: 4.3382. Min Act: -0.0000

Data Index: 309943 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 5.7775. Min Range: -5.7775

Max Act: 4.2511. Min Act: -0.0000

Data Index: 1190248 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 5.7775. Min Range: -5.7775

Max Act: 4.1527. Min Act: -0.0000

Data Index: 968412 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 5.7775. Min Range: -5.7775

Max Act: 3.9750. Min Act: -0.0000

Data Index: 1346364 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 5.7775. Min Range: -5.7775

Max Act: 3.8922. Min Act: -0.0000

Data Index: 140158 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 5.7775. Min Range: -5.7775

Max Act: 4.0121. Min Act: -0.0000

Data Index: 397560 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 5.7775. Min Range: -5.7775

Max Act: 3.9767. Min Act: -0.0000

Data Index: 1108149 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 5.7775. Min Range: -5.7775

Max Act: 3.6668. Min Act: -0.0000

Data Index: 1349116 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 5.7775. Min Range: -5.7775

Max Act: 3.9868. Min Act: -0.0000

Data Index: 747992 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 5.7775. Min Range: -5.7775

Max Act: 3.7585. Min Act: -0.0000

Data Index: 603186 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 5.7775. Min Range: -5.7775

Max Act: 3.6134. Min Act: -0.0000

Data Index: 333208 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 5.7775. Min Range: -5.7775

Max Act: 3.7526. Min Act: -0.0000

Data Index: 170578 (C4 (Web Text))

Max Activating Token Index: 114