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

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

Neuron 250 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: 1.0992. Min Range: -1.0992

Max Act: 1.0992. Min Act: -0.0000

Data Index: 686562 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 1.0992. Min Range: -1.0992

Max Act: 1.0683. Min Act: -0.0000

Data Index: 779986 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 1.0992. Min Range: -1.0992

Max Act: 1.0019. Min Act: -0.0000

Data Index: 501346 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 1.0992. Min Range: -1.0992

Max Act: 1.0469. Min Act: -0.0000

Data Index: 220437 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 1.0992. Min Range: -1.0992

Max Act: 1.0503. Min Act: -0.0000

Data Index: 786448 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9344. Min Act: -0.0000

Data Index: 954101 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 1.0992. Min Range: -1.0992

Max Act: 1.0877. Min Act: -0.0000

Data Index: 887049 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1126482 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 1.0992. Min Range: -1.0992

Max Act: 1.0227. Min Act: -0.0000

Data Index: 253881 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9470. Min Act: -0.0000

Data Index: 667884 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9343. Min Act: -0.0000

Data Index: 135404 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9207. Min Act: -0.0000

Data Index: 437311 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.8871. Min Act: -0.0000

Data Index: 161052 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.8744. Min Act: -0.0000

Data Index: 195462 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9018. Min Act: -0.0000

Data Index: 243590 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1255082 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1071837 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.8509. Min Act: -0.0000

Data Index: 400328 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.8748. Min Act: -0.0000

Data Index: 191933 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.8149. Min Act: -0.0000

Data Index: 346075 (C4 (Web Text))

Max Activating Token Index: 325