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

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

Neuron 4354 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1481. Min Act: -0.0000

Data Index: 60428 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1273272 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1454. Min Act: -0.0000

Data Index: 345729 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1442. Min Act: -0.0000

Data Index: 731535 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1604359 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1459886 (Python Code)

Max Activating Token Index: 295

Text #6

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1453580 (Python Code)

Max Activating Token Index: 680

Text #7

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1548737 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1237. Min Act: -0.0000

Data Index: 776819 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1528517 (Python Code)

Max Activating Token Index: 545

Text #10

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1212. Min Act: -0.0000

Data Index: 71507 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1496444 (Python Code)

Max Activating Token Index: 15

Text #12

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1104. Min Act: -0.0000

Data Index: 738107 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1378793 (Python Code)

Max Activating Token Index: 936

Text #14

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1102. Min Act: -0.0000

Data Index: 777790 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1239646 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1160083 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1089. Min Act: -0.0000

Data Index: 801982 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1529146 (Python Code)

Max Activating Token Index: 609

Text #19

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1528182 (Python Code)

Max Activating Token Index: 456