Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2075 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1631. Min Act: -0.0003

Data Index: 760677 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1630. Min Act: -0.0003

Data Index: 442833 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1449. Min Act: -0.0003

Data Index: 212662 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1412. Min Act: -0.0003

Data Index: 1294711 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1357. Min Act: -0.0003

Data Index: 216856 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1427. Min Act: -0.0003

Data Index: 1128437 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1439. Min Act: -0.0003

Data Index: 690703 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1456. Min Act: -0.0003

Data Index: 694491 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1390. Min Act: -0.0003

Data Index: 391495 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1323. Min Act: -0.0003

Data Index: 184795 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1456. Min Act: -0.0003

Data Index: 624862 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1218. Min Act: -0.0003

Data Index: 1080590 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1531. Min Act: -0.0003

Data Index: 343238 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1290. Min Act: -0.0003

Data Index: 766802 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1387. Min Act: -0.0003

Data Index: 681221 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1338. Min Act: -0.0003

Data Index: 1058544 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1427. Min Act: -0.0003

Data Index: 182127 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1359. Min Act: -0.0003

Data Index: 618553 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1492. Min Act: -0.0003

Data Index: 1107437 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1343. Min Act: -0.0003

Data Index: 1010710 (C4 (Web Text))

Max Activating Token Index: 962