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

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

Neuron 3063 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1495. Min Range: -2.1495

Max Act: 2.1495. Min Act: -0.0000

Data Index: 907334 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 2.1495. Min Range: -2.1495

Max Act: 2.1198. Min Act: -0.0000

Data Index: 543054 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 2.1495. Min Range: -2.1495

Max Act: 1.7978. Min Act: -0.0000

Data Index: 248610 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 2.1495. Min Range: -2.1495

Max Act: 1.5240. Min Act: -0.0000

Data Index: 552912 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 2.1495. Min Range: -2.1495

Max Act: 1.4905. Min Act: -0.0000

Data Index: 807439 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 2.1495. Min Range: -2.1495

Max Act: 1.3665. Min Act: -0.0000

Data Index: 147254 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 2.1495. Min Range: -2.1495

Max Act: 1.4342. Min Act: -0.0000

Data Index: 1268499 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 2.1495. Min Range: -2.1495

Max Act: 1.2274. Min Act: -0.0000

Data Index: 169192 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 2.1495. Min Range: -2.1495

Max Act: 0.9487. Min Act: -0.0000

Data Index: 282427 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 2.1495. Min Range: -2.1495

Max Act: 1.0608. Min Act: -0.0000

Data Index: 10653 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 2.1495. Min Range: -2.1495

Max Act: 1.0955. Min Act: -0.0000

Data Index: 626651 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 2.1495. Min Range: -2.1495

Max Act: 1.2290. Min Act: -0.0000

Data Index: 878897 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 2.1495. Min Range: -2.1495

Max Act: 1.0245. Min Act: -0.0000

Data Index: 313246 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 2.1495. Min Range: -2.1495

Max Act: 0.8901. Min Act: -0.0000

Data Index: 1143495 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 2.1495. Min Range: -2.1495

Max Act: 0.9420. Min Act: -0.0000

Data Index: 338832 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 2.1495. Min Range: -2.1495

Max Act: 0.9190. Min Act: -0.0000

Data Index: 1130316 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 2.1495. Min Range: -2.1495

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1377576 (Python Code)

Max Activating Token Index: 572

Text #17

Max Range: 2.1495. Min Range: -2.1495

Max Act: 0.9064. Min Act: -0.0000

Data Index: 419666 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 2.1495. Min Range: -2.1495

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1271186 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 2.1495. Min Range: -2.1495

Max Act: 0.8562. Min Act: -0.0000

Data Index: 150223 (C4 (Web Text))

Max Activating Token Index: 631