Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1572 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1597. Min Act: -0.0002

Data Index: 1321031 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1599. Min Act: -0.0002

Data Index: 416010 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1483. Min Act: -0.0002

Data Index: 621035 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1482. Min Act: -0.0002

Data Index: 464413 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1351. Min Act: -0.0002

Data Index: 964839 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1375. Min Act: -0.0002

Data Index: 721130 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1352. Min Act: -0.0002

Data Index: 473076 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1342. Min Act: -0.0002

Data Index: 415040 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1366. Min Act: -0.0002

Data Index: 738966 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1287. Min Act: -0.0002

Data Index: 396948 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1283. Min Act: -0.0002

Data Index: 176803 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1315. Min Act: -0.0002

Data Index: 244243 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1360. Min Act: -0.0002

Data Index: 718784 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1354. Min Act: -0.0002

Data Index: 844334 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1296. Min Act: -0.0002

Data Index: 1290753 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1270. Min Act: -0.0002

Data Index: 238241 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1280. Min Act: -0.0002

Data Index: 673648 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1250. Min Act: -0.0002

Data Index: 1190342 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1240. Min Act: -0.0002

Data Index: 1050354 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1224. Min Act: -0.0002

Data Index: 47909 (C4 (Web Text))

Max Activating Token Index: 347