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

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

Neuron 4027 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.8658. Min Act: -0.0001

Data Index: 1327784 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.7841. Min Act: -0.0001

Data Index: 277552 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.6006. Min Act: -0.0001

Data Index: 1244736 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.6625. Min Act: -0.0001

Data Index: 655457 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.6389. Min Act: -0.0001

Data Index: 115274 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.4331. Min Act: -0.0001

Data Index: 874932 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.4954. Min Act: -0.0001

Data Index: 685541 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.4425. Min Act: -0.0001

Data Index: 586815 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.3832. Min Act: -0.0001

Data Index: 1041438 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.3804. Min Act: -0.0001

Data Index: 1343726 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.4077. Min Act: -0.0001

Data Index: 125300 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.4017. Min Act: -0.0001

Data Index: 15284 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.3251. Min Act: -0.0001

Data Index: 616262 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.3231. Min Act: -0.0001

Data Index: 1240469 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.2953. Min Act: -0.0001

Data Index: 67014 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.3315. Min Act: -0.0001

Data Index: 349750 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.2808. Min Act: -0.0001

Data Index: 191236 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.3298. Min Act: -0.0001

Data Index: 604506 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.2353. Min Act: -0.0001

Data Index: 962096 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 1.8658. Min Range: -1.8658

Max Act: 1.2299. Min Act: -0.0001

Data Index: 13461 (C4 (Web Text))

Max Activating Token Index: 297