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

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

Neuron 5480 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2289. Min Range: -3.2289

Max Act: 3.2289. Min Act: -0.0000

Data Index: 805 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.8129. Min Act: -0.0000

Data Index: 507743 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.9414. Min Act: -0.0000

Data Index: 621763 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.8237. Min Act: -0.0000

Data Index: 1299402 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.8506. Min Act: -0.0000

Data Index: 906191 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.6740. Min Act: -0.0000

Data Index: 366306 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.6218. Min Act: -0.0000

Data Index: 1265707 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.4884. Min Act: -0.0000

Data Index: 999192 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.4378. Min Act: -0.0000

Data Index: 650479 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.3935. Min Act: -0.0000

Data Index: 1105096 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.3527. Min Act: -0.0000

Data Index: 954818 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.3279. Min Act: -0.0000

Data Index: 546274 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.3009. Min Act: -0.0000

Data Index: 894434 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.3951. Min Act: -0.0000

Data Index: 1479370 (Python Code)

Max Activating Token Index: 43

Text #14

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.1443. Min Act: -0.0000

Data Index: 225928 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.2530. Min Act: -0.0000

Data Index: 38111 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.2364. Min Act: -0.0000

Data Index: 559665 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.1007. Min Act: -0.0000

Data Index: 107569 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.2163. Min Act: -0.0000

Data Index: 956500 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 3.2289. Min Range: -3.2289

Max Act: 2.2116. Min Act: -0.0000

Data Index: 1277651 (C4 (Web Text))

Max Activating Token Index: 276