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

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

Neuron 2024 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3355. Min Range: -2.3355

Max Act: 2.3355. Min Act: -0.0000

Data Index: 1088020 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.9363. Min Act: -0.0000

Data Index: 1027844 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 2.3355. Min Range: -2.3355

Max Act: 2.0141. Min Act: -0.0000

Data Index: 378960 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.9561. Min Act: -0.0000

Data Index: 322219 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.9932. Min Act: -0.0000

Data Index: 354664 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.9250. Min Act: -0.0000

Data Index: 1114651 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.7667. Min Act: -0.0000

Data Index: 879967 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.7417. Min Act: -0.0000

Data Index: 446663 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.6994. Min Act: -0.0000

Data Index: 132001 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.6862. Min Act: -0.0000

Data Index: 297061 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.7729. Min Act: -0.0000

Data Index: 801642 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.6772. Min Act: -0.0000

Data Index: 1252482 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.7552. Min Act: -0.0000

Data Index: 673238 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.6377. Min Act: -0.0000

Data Index: 1331090 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.6868. Min Act: -0.0000

Data Index: 459454 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.5881. Min Act: -0.0000

Data Index: 821740 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.5768. Min Act: -0.0000

Data Index: 1060350 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.5892. Min Act: -0.0000

Data Index: 247533 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.4860. Min Act: -0.0000

Data Index: 64067 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 2.3355. Min Range: -2.3355

Max Act: 1.5752. Min Act: -0.0000

Data Index: 295573 (C4 (Web Text))

Max Activating Token Index: 358