Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3283 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.2110. Min Act: -0.0000

Data Index: 540066 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.2592. Min Act: 0.0000

Data Index: 602382 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.9343. Min Act: 0.0000

Data Index: 507492 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.8642. Min Act: -0.0000

Data Index: 889049 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1000973 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7663. Min Act: 0.0000

Data Index: 850160 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7756. Min Act: -0.0000

Data Index: 135247 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1165949 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7843. Min Act: -0.0000

Data Index: 905696 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1144165 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7259. Min Act: -0.0000

Data Index: 196761 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7104. Min Act: -0.0000

Data Index: 251860 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.6914. Min Act: -0.0000

Data Index: 506344 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.6782. Min Act: -0.0000

Data Index: 151985 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7467. Min Act: -0.0000

Data Index: 857556 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.6925. Min Act: -0.0000

Data Index: 107896 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.6557. Min Act: -0.0000

Data Index: 93740 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.6692. Min Act: -0.0000

Data Index: 52329 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.6380. Min Act: -0.0000

Data Index: 12388 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.6526. Min Act: 0.0000

Data Index: 1037193 (C4 (Web Text))

Max Activating Token Index: 454