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

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

Neuron 4453 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.8953. Min Act: -0.0000

Data Index: 867264 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.9035. Min Act: -0.0000

Data Index: 59057 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.8671. Min Act: -0.0000

Data Index: 1286876 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.8268. Min Act: -0.0000

Data Index: 1202460 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.7034. Min Act: -0.0000

Data Index: 1224172 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.5379. Min Act: -0.0000

Data Index: 561463 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.6129. Min Act: -0.0000

Data Index: 623982 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.5366. Min Act: -0.0000

Data Index: 668633 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.5982. Min Act: -0.0000

Data Index: 1309049 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.4457. Min Act: -0.0000

Data Index: 97019 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.5467. Min Act: -0.0000

Data Index: 560194 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.5333. Min Act: -0.0000

Data Index: 1005413 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.5755. Min Act: -0.0000

Data Index: 317102 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.4803. Min Act: -0.0000

Data Index: 1315627 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.4892. Min Act: -0.0000

Data Index: 1173167 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.4524. Min Act: -0.0000

Data Index: 535535 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.4885. Min Act: -0.0000

Data Index: 515114 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.4804. Min Act: -0.0000

Data Index: 1137897 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.4745. Min Act: -0.0000

Data Index: 1022756 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 1.9035. Min Range: -1.9035

Max Act: 1.5095. Min Act: -0.0000

Data Index: 387886 (C4 (Web Text))

Max Activating Token Index: 284