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

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

Neuron 3188 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: 1.5289. Min Range: -1.5289

Max Act: 1.4326. Min Act: -0.0001

Data Index: 416232 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.5289. Min Act: -0.0001

Data Index: 1424118 (Python Code)

Max Activating Token Index: 277

Text #2

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1403. Min Act: -0.0001

Data Index: 1375082 (Python Code)

Max Activating Token Index: 320

Text #3

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.3276. Min Act: -0.0001

Data Index: 328525 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1960. Min Act: -0.0001

Data Index: 1321156 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1298. Min Act: -0.0001

Data Index: 29746 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.2164. Min Act: -0.0001

Data Index: 1627823 (Python Code)

Max Activating Token Index: 703

Text #7

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1399. Min Act: -0.0001

Data Index: 769065 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1315. Min Act: -0.0001

Data Index: 1113778 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1412. Min Act: -0.0001

Data Index: 702992 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.0736. Min Act: -0.0001

Data Index: 1486307 (Python Code)

Max Activating Token Index: 733

Text #11

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1701. Min Act: -0.0001

Data Index: 1098339 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.0108. Min Act: -0.0001

Data Index: 670256 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.1075. Min Act: -0.0001

Data Index: 1044574 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.0427. Min Act: -0.0001

Data Index: 729205 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.0471. Min Act: -0.0001

Data Index: 1511979 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.0445. Min Act: -0.0001

Data Index: 107091 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.0211. Min Act: -0.0001

Data Index: 143173 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 1.5289. Min Range: -1.5289

Max Act: 0.9818. Min Act: -0.0001

Data Index: 991494 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.5289. Min Range: -1.5289

Max Act: 1.0088. Min Act: -0.0001

Data Index: 711565 (C4 (Web Text))

Max Activating Token Index: 212