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

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

Neuron 4496 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.4550. Min Act: -0.0002

Data Index: 125673 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.2768. Min Act: -0.0002

Data Index: 1298913 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.3396. Min Act: -0.0002

Data Index: 1175416 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.3760. Min Act: -0.0002

Data Index: 290924 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.3025. Min Act: -0.0002

Data Index: 1035221 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.1875. Min Act: -0.0002

Data Index: 1020814 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.2061. Min Act: -0.0002

Data Index: 175693 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.1741. Min Act: -0.0002

Data Index: 723585 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.0584. Min Act: -0.0002

Data Index: 876906 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.1269. Min Act: -0.0002

Data Index: 235172 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.1473. Min Act: -0.0002

Data Index: 882362 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 1.4550. Min Range: -1.4550

Max Act: 0.9343. Min Act: -0.0002

Data Index: 364953 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.0567. Min Act: -0.0002

Data Index: 1001285 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.1067. Min Act: -0.0002

Data Index: 966642 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.1283. Min Act: -0.0002

Data Index: 510200 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.0663. Min Act: -0.0002

Data Index: 204720 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.0207. Min Act: -0.0002

Data Index: 1064213 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 1.4550. Min Range: -1.4550

Max Act: 0.9293. Min Act: -0.0002

Data Index: 1251931 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 1.4550. Min Range: -1.4550

Max Act: 0.9608. Min Act: -0.0002

Data Index: 1218571 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 1.4550. Min Range: -1.4550

Max Act: 0.8329. Min Act: -0.0002

Data Index: 570322 (C4 (Web Text))

Max Activating Token Index: 548