Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 676 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.5389. Min Act: -0.0000

Data Index: 1326570 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.3444. Min Act: -0.0000

Data Index: 944589 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.2560. Min Act: -0.0000

Data Index: 1315053 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.1339. Min Act: -0.0000

Data Index: 1172973 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.1975. Min Act: -0.0000

Data Index: 278200 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.1160. Min Act: -0.0000

Data Index: 262317 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.1573. Min Act: -0.0000

Data Index: 1117413 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.1394. Min Act: -0.0000

Data Index: 68318 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.0103. Min Act: -0.0000

Data Index: 12477 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.0885. Min Act: -0.0000

Data Index: 1001576 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.0509. Min Act: -0.0000

Data Index: 443785 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1340251 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.9680. Min Act: -0.0000

Data Index: 745711 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.0292. Min Act: -0.0000

Data Index: 67691 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.9916. Min Act: -0.0000

Data Index: 743489 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.9550. Min Act: -0.0000

Data Index: 730558 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1167718 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1175497 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 1.5389. Min Range: -1.5389

Max Act: 0.9681. Min Act: -0.0000

Data Index: 278460 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 1.5389. Min Range: -1.5389

Max Act: 1.0199. Min Act: -0.0000

Data Index: 42833 (C4 (Web Text))

Max Activating Token Index: 324