Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1303 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2330. Min Act: -0.0001

Data Index: 130444 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2263. Min Act: -0.0001

Data Index: 367859 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2402. Min Act: -0.0000

Data Index: 934012 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2048. Min Act: -0.0000

Data Index: 265529 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2105. Min Act: -0.0001

Data Index: 1078666 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1112328 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2028. Min Act: -0.0001

Data Index: 240274 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2103. Min Act: -0.0000

Data Index: 627588 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2014. Min Act: -0.0001

Data Index: 8778 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2152. Min Act: -0.0001

Data Index: 181011 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2082. Min Act: -0.0001

Data Index: 228538 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1924. Min Act: -0.0000

Data Index: 90014 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1863. Min Act: -0.0000

Data Index: 1280947 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1850. Min Act: -0.0001

Data Index: 828936 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1853. Min Act: -0.0000

Data Index: 795667 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1875. Min Act: -0.0000

Data Index: 133180 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1873. Min Act: -0.0000

Data Index: 676626 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1064786 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1845. Min Act: -0.0001

Data Index: 122449 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1971. Min Act: -0.0000

Data Index: 860506 (C4 (Web Text))

Max Activating Token Index: 433