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

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

Neuron 1622 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7397. Min Range: -3.7397

Max Act: 3.7397. Min Act: -0.0000

Data Index: 631138 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 3.7397. Min Range: -3.7397

Max Act: 2.3986. Min Act: -0.0000

Data Index: 168628 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 3.7397. Min Range: -3.7397

Max Act: 2.2228. Min Act: -0.0000

Data Index: 391701 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 3.7397. Min Range: -3.7397

Max Act: 2.1868. Min Act: -0.0000

Data Index: 157311 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 3.7397. Min Range: -3.7397

Max Act: 2.2149. Min Act: -0.0000

Data Index: 202639 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 3.7397. Min Range: -3.7397

Max Act: 2.0636. Min Act: -0.0000

Data Index: 1038592 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 3.7397. Min Range: -3.7397

Max Act: 2.1072. Min Act: -0.0000

Data Index: 1304491 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 3.7397. Min Range: -3.7397

Max Act: 2.0776. Min Act: -0.0000

Data Index: 422629 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 3.7397. Min Range: -3.7397

Max Act: 1.9730. Min Act: -0.0000

Data Index: 412109 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 3.7397. Min Range: -3.7397

Max Act: 1.9868. Min Act: -0.0000

Data Index: 1224963 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 3.7397. Min Range: -3.7397

Max Act: 1.9970. Min Act: -0.0000

Data Index: 1030365 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 3.7397. Min Range: -3.7397

Max Act: 1.9920. Min Act: -0.0000

Data Index: 1197447 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 3.7397. Min Range: -3.7397

Max Act: 1.9502. Min Act: -0.0000

Data Index: 811181 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 3.7397. Min Range: -3.7397

Max Act: 1.9308. Min Act: -0.0000

Data Index: 839050 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 3.7397. Min Range: -3.7397

Max Act: 1.9281. Min Act: -0.0000

Data Index: 480257 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 3.7397. Min Range: -3.7397

Max Act: 1.9076. Min Act: -0.0000

Data Index: 87765 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 3.7397. Min Range: -3.7397

Max Act: 1.6796. Min Act: -0.0000

Data Index: 1340114 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 3.7397. Min Range: -3.7397

Max Act: 1.8487. Min Act: -0.0000

Data Index: 775640 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 3.7397. Min Range: -3.7397

Max Act: 1.8565. Min Act: -0.0000

Data Index: 1204603 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 3.7397. Min Range: -3.7397

Max Act: 1.7330. Min Act: -0.0000

Data Index: 1125278 (C4 (Web Text))

Max Activating Token Index: 343