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

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

Neuron 5427 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.8608. Min Act: -0.0000

Data Index: 700308 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.9066. Min Act: -0.0000

Data Index: 408316 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.8649. Min Act: -0.0000

Data Index: 233497 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.8381. Min Act: -0.0000

Data Index: 245542 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.9298. Min Act: -0.0000

Data Index: 659740 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.8374. Min Act: -0.0000

Data Index: 742119 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.8082. Min Act: -0.0000

Data Index: 276314 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.7560. Min Act: -0.0000

Data Index: 290567 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1492980 (Python Code)

Max Activating Token Index: 470

Text #9

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.7250. Min Act: -0.0000

Data Index: 123783 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1566474 (Python Code)

Max Activating Token Index: 450

Text #11

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.7078. Min Act: -0.0000

Data Index: 325135 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1627709 (Python Code)

Max Activating Token Index: 519

Text #13

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.7129. Min Act: -0.0000

Data Index: 876842 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1209389 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1304145 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.6751. Min Act: -0.0000

Data Index: 678122 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1505790 (Python Code)

Max Activating Token Index: 110

Text #18

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.6831. Min Act: -0.0000

Data Index: 257844 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.9298. Min Range: -0.9298

Max Act: 0.7086. Min Act: -0.0000

Data Index: 998513 (C4 (Web Text))

Max Activating Token Index: 306