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

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

Neuron 1991 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.2582. Min Act: -0.0000

Data Index: 25893 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.3510. Min Act: -0.0000

Data Index: 549353 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.1947. Min Act: -0.0000

Data Index: 988223 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.1931. Min Act: -0.0000

Data Index: 1065578 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.1556. Min Act: -0.0000

Data Index: 163710 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.4054. Min Act: -0.0000

Data Index: 1141193 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.9609. Min Act: -0.0000

Data Index: 586025 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.1689. Min Act: -0.0000

Data Index: 155195 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.2052. Min Act: -0.0000

Data Index: 284912 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.1160. Min Act: -0.0000

Data Index: 136371 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.0746. Min Act: -0.0000

Data Index: 383130 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.1716. Min Act: -0.0000

Data Index: 908234 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.0384. Min Act: -0.0000

Data Index: 475483 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.1925. Min Act: -0.0000

Data Index: 761303 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.0910. Min Act: -0.0000

Data Index: 1159348 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.8026. Min Act: -0.0000

Data Index: 517458 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.1083. Min Act: -0.0000

Data Index: 1097210 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 2.4054. Min Range: -2.4054

Max Act: 1.9154. Min Act: -0.0000

Data Index: 1326614 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.1909. Min Act: -0.0000

Data Index: 282090 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 2.4054. Min Range: -2.4054

Max Act: 2.0612. Min Act: -0.0000

Data Index: 989385 (C4 (Web Text))

Max Activating Token Index: 765