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

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

Neuron 1496 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1462. Min Range: -4.1462

Max Act: 4.1462. Min Act: -0.0000

Data Index: 109270 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 4.1462. Min Range: -4.1462

Max Act: 4.0143. Min Act: -0.0000

Data Index: 1062806 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 4.1462. Min Range: -4.1462

Max Act: 3.9303. Min Act: -0.0000

Data Index: 319202 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 4.1462. Min Range: -4.1462

Max Act: 3.4584. Min Act: -0.0000

Data Index: 1083887 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 4.1462. Min Range: -4.1462

Max Act: 3.4868. Min Act: -0.0000

Data Index: 692922 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 4.1462. Min Range: -4.1462

Max Act: 3.3314. Min Act: -0.0000

Data Index: 1216819 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 4.1462. Min Range: -4.1462

Max Act: 3.3060. Min Act: -0.0000

Data Index: 1165812 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 4.1462. Min Range: -4.1462

Max Act: 3.5264. Min Act: -0.0000

Data Index: 521099 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 4.1462. Min Range: -4.1462

Max Act: 3.4061. Min Act: -0.0000

Data Index: 521556 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 4.1462. Min Range: -4.1462

Max Act: 3.2184. Min Act: -0.0000

Data Index: 903239 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 4.1462. Min Range: -4.1462

Max Act: 2.6548. Min Act: -0.0000

Data Index: 523469 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 4.1462. Min Range: -4.1462

Max Act: 2.7891. Min Act: -0.0000

Data Index: 1180320 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 4.1462. Min Range: -4.1462

Max Act: 2.8822. Min Act: -0.0000

Data Index: 1312732 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 4.1462. Min Range: -4.1462

Max Act: 2.8151. Min Act: -0.0000

Data Index: 920094 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 4.1462. Min Range: -4.1462

Max Act: 2.7491. Min Act: -0.0000

Data Index: 254495 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 4.1462. Min Range: -4.1462

Max Act: 2.5961. Min Act: -0.0000

Data Index: 104419 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 4.1462. Min Range: -4.1462

Max Act: 2.4598. Min Act: -0.0000

Data Index: 1473703 (Python Code)

Max Activating Token Index: 731

Text #17

Max Range: 4.1462. Min Range: -4.1462

Max Act: 2.4289. Min Act: -0.0000

Data Index: 603237 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 4.1462. Min Range: -4.1462

Max Act: 2.2280. Min Act: -0.0000

Data Index: 1297789 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 4.1462. Min Range: -4.1462

Max Act: 2.3972. Min Act: -0.0000

Data Index: 302365 (C4 (Web Text))

Max Activating Token Index: 386