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

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

Neuron 6084 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: 0.6400. Min Range: -0.6400

Max Act: 0.6400. Min Act: -0.0000

Data Index: 433980 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.6088. Min Act: -0.0000

Data Index: 313016 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1267120 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1309341 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.5173. Min Act: -0.0000

Data Index: 211147 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.5104. Min Act: -0.0000

Data Index: 5189 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.5260. Min Act: -0.0000

Data Index: 120634 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4766. Min Act: -0.0000

Data Index: 928322 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1087275 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4984. Min Act: -0.0000

Data Index: 643078 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4618. Min Act: -0.0000

Data Index: 956484 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4935. Min Act: -0.0000

Data Index: 165762 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4559. Min Act: -0.0000

Data Index: 221950 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4851. Min Act: -0.0000

Data Index: 51728 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4679. Min Act: -0.0000

Data Index: 375599 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.5018. Min Act: -0.0000

Data Index: 872072 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4564. Min Act: -0.0000

Data Index: 748905 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1154504 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1168787 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1217044 (C4 (Web Text))

Max Activating Token Index: 509