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

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

Neuron 130 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.4234. Min Act: -0.0001

Data Index: 1358448 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.4339. Min Act: -0.0001

Data Index: 128696 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3657. Min Act: -0.0001

Data Index: 172648 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3206. Min Act: -0.0001

Data Index: 102782 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3531. Min Act: -0.0001

Data Index: 993933 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3534. Min Act: -0.0001

Data Index: 417017 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3525. Min Act: -0.0001

Data Index: 651661 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3391. Min Act: -0.0001

Data Index: 893769 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3431. Min Act: -0.0001

Data Index: 723803 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2959. Min Act: -0.0001

Data Index: 1162637 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3268. Min Act: -0.0001

Data Index: 1301126 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3201. Min Act: -0.0001

Data Index: 651985 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3048. Min Act: -0.0001

Data Index: 615329 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3082. Min Act: -0.0001

Data Index: 825485 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2972. Min Act: -0.0001

Data Index: 1030927 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2954. Min Act: -0.0001

Data Index: 218720 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3023. Min Act: -0.0001

Data Index: 382694 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2952. Min Act: -0.0001

Data Index: 782838 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2880. Min Act: -0.0001

Data Index: 344848 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2983. Min Act: -0.0001

Data Index: 823608 (C4 (Web Text))

Max Activating Token Index: 37