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

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

Neuron 4606 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6143. Min Range: -2.6143

Max Act: 2.6143. Min Act: -0.0000

Data Index: 448936 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 2.6143. Min Range: -2.6143

Max Act: 2.3360. Min Act: -0.0000

Data Index: 766648 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.9375. Min Act: -0.0000

Data Index: 609462 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.8220. Min Act: -0.0000

Data Index: 832883 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.9452. Min Act: -0.0000

Data Index: 1327677 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.7714. Min Act: -0.0000

Data Index: 787965 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.8497. Min Act: -0.0000

Data Index: 472574 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.8334. Min Act: -0.0000

Data Index: 886518 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.8315. Min Act: -0.0000

Data Index: 622251 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.8292. Min Act: -0.0000

Data Index: 506531 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.7086. Min Act: -0.0000

Data Index: 701342 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.7517. Min Act: -0.0000

Data Index: 1301195 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.6306. Min Act: -0.0000

Data Index: 1148155 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.7210. Min Act: -0.0000

Data Index: 1266583 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.7109. Min Act: -0.0000

Data Index: 8379 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.6127. Min Act: -0.0000

Data Index: 871656 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.6950. Min Act: -0.0000

Data Index: 1284023 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.5998. Min Act: -0.0000

Data Index: 528574 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.5982. Min Act: -0.0000

Data Index: 956010 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 2.6143. Min Range: -2.6143

Max Act: 1.6917. Min Act: -0.0000

Data Index: 273267 (C4 (Web Text))

Max Activating Token Index: 920