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

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

Neuron 4015 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: 0.9995. Min Range: -0.9995

Max Act: 0.9995. Min Act: -0.0000

Data Index: 538740 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.8583. Min Act: -0.0000

Data Index: 42157 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7334. Min Act: -0.0000

Data Index: 142915 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7547. Min Act: -0.0000

Data Index: 353406 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7761. Min Act: -0.0000

Data Index: 825623 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7508. Min Act: -0.0000

Data Index: 214448 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7203. Min Act: -0.0000

Data Index: 930962 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7530. Min Act: -0.0000

Data Index: 893359 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7229. Min Act: -0.0000

Data Index: 466668 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1110349 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1209313 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6842. Min Act: -0.0000

Data Index: 419023 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6788. Min Act: -0.0000

Data Index: 123699 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6604. Min Act: -0.0000

Data Index: 866034 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6816. Min Act: -0.0000

Data Index: 572983 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6253. Min Act: -0.0000

Data Index: 797081 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6592. Min Act: -0.0000

Data Index: 141100 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6200. Min Act: -0.0000

Data Index: 690009 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6596. Min Act: -0.0000

Data Index: 177124 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.9995. Min Range: -0.9995

Max Act: 0.6368. Min Act: -0.0000

Data Index: 18876 (C4 (Web Text))

Max Activating Token Index: 38