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

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

Neuron 3674 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: 0.2300. Min Range: -0.2300

Max Act: 0.2300. Min Act: -0.0000

Data Index: 847138 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1848. Min Act: -0.0000

Data Index: 278666 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1720. Min Act: -0.0000

Data Index: 787195 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1661. Min Act: -0.0000

Data Index: 735217 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1647. Min Act: -0.0000

Data Index: 346343 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1299967 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1080385 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1396. Min Act: -0.0000

Data Index: 155499 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1444. Min Act: -0.0000

Data Index: 959626 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1435. Min Act: -0.0000

Data Index: 508795 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1413. Min Act: -0.0000

Data Index: 837214 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1363. Min Act: -0.0000

Data Index: 380361 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1311. Min Act: -0.0000

Data Index: 365260 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1295. Min Act: -0.0000

Data Index: 785581 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1198. Min Act: -0.0000

Data Index: 541495 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1137292 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1232. Min Act: -0.0000

Data Index: 624520 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1261. Min Act: -0.0000

Data Index: 618021 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1108. Min Act: -0.0000

Data Index: 146611 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.2300. Min Range: -0.2300

Max Act: 0.1206. Min Act: -0.0000

Data Index: 38825 (C4 (Web Text))

Max Activating Token Index: 616