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

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

Neuron 1356 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.2266. Min Act: -0.0001

Data Index: 62203 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.2057. Min Act: -0.0001

Data Index: 741773 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1901. Min Act: -0.0000

Data Index: 1123974 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1530. Min Act: -0.0001

Data Index: 396472 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1623. Min Act: -0.0001

Data Index: 272742 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1610. Min Act: -0.0000

Data Index: 1004990 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1670. Min Act: -0.0001

Data Index: 184835 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1317. Min Act: -0.0000

Data Index: 421341 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1369. Min Act: -0.0001

Data Index: 1022131 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1445. Min Act: -0.0001

Data Index: 55708 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1343. Min Act: -0.0001

Data Index: 915278 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1606. Min Act: -0.0001

Data Index: 1185393 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1265. Min Act: -0.0000

Data Index: 636465 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1049. Min Act: -0.0001

Data Index: 261923 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1040. Min Act: -0.0000

Data Index: 957145 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1001. Min Act: -0.0001

Data Index: 267964 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1232186 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.0976. Min Act: -0.0001

Data Index: 978216 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.0977. Min Act: -0.0000

Data Index: 953345 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.2266. Min Range: -0.2266

Max Act: 0.0850. Min Act: -0.0001

Data Index: 491671 (C4 (Web Text))

Max Activating Token Index: 866