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

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

Neuron 1615 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1908. Min Act: -0.0001

Data Index: 1533026 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1671. Min Act: -0.0000

Data Index: 230706 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1636. Min Act: 0.0001

Data Index: 628546 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1693. Min Act: -0.0001

Data Index: 1318217 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1575. Min Act: -0.0001

Data Index: 978019 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1547. Min Act: -0.0000

Data Index: 41429 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1077267 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1531. Min Act: -0.0001

Data Index: 730123 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1426. Min Act: -0.0001

Data Index: 514109 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1166070 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1222595 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1144303 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1364. Min Act: -0.0000

Data Index: 584236 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1358. Min Act: -0.0000

Data Index: 942144 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1343. Min Act: -0.0001

Data Index: 725785 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1296. Min Act: -0.0001

Data Index: 427494 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1196. Min Act: -0.0000

Data Index: 470396 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1303. Min Act: -0.0001

Data Index: 159564 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1112888 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1122965 (C4 (Web Text))

Max Activating Token Index: 1018