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

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

Neuron 1767 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: 2.0464. Min Range: -2.0464

Max Act: 2.0464. Min Act: -0.0000

Data Index: 1010414 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.6255. Min Act: -0.0000

Data Index: 123551 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.5625. Min Act: -0.0000

Data Index: 153289 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.5416. Min Act: -0.0000

Data Index: 779194 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.4386. Min Act: -0.0000

Data Index: 772566 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.4275. Min Act: -0.0001

Data Index: 910789 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.3274. Min Act: -0.0000

Data Index: 1119207 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.3855. Min Act: -0.0000

Data Index: 952838 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.2158. Min Act: -0.0000

Data Index: 23142 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.3471. Min Act: -0.0000

Data Index: 51150 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.2577. Min Act: -0.0000

Data Index: 1141124 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.1749. Min Act: -0.0000

Data Index: 164764 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.1878. Min Act: -0.0000

Data Index: 689069 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.2679. Min Act: -0.0000

Data Index: 516776 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.3389. Min Act: -0.0000

Data Index: 1245172 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.1773. Min Act: -0.0000

Data Index: 1181791 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.0450. Min Act: -0.0000

Data Index: 1178360 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.0879. Min Act: -0.0000

Data Index: 789730 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.0842. Min Act: -0.0000

Data Index: 685041 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 2.0464. Min Range: -2.0464

Max Act: 1.1535. Min Act: -0.0000

Data Index: 982305 (C4 (Web Text))

Max Activating Token Index: 129