Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 798 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1631. Min Act: -0.0003

Data Index: 35115 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1777. Min Act: -0.0003

Data Index: 1200546 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1548. Min Act: -0.0004

Data Index: 1075462 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1563. Min Act: -0.0003

Data Index: 70347 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1389. Min Act: -0.0003

Data Index: 708779 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1519. Min Act: -0.0003

Data Index: 871302 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1436. Min Act: -0.0003

Data Index: 1344692 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1428. Min Act: -0.0003

Data Index: 170152 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1346. Min Act: -0.0003

Data Index: 701890 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1335. Min Act: -0.0003

Data Index: 69517 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1474. Min Act: -0.0003

Data Index: 535873 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1412. Min Act: -0.0003

Data Index: 1352605 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1305. Min Act: -0.0003

Data Index: 1192735 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1203. Min Act: -0.0003

Data Index: 693121 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1339. Min Act: -0.0003

Data Index: 521504 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1231. Min Act: -0.0003

Data Index: 889107 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1262. Min Act: -0.0003

Data Index: 856956 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1361. Min Act: -0.0003

Data Index: 809274 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1305. Min Act: -0.0003

Data Index: 1023705 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1403. Min Act: -0.0003

Data Index: 470696 (C4 (Web Text))

Max Activating Token Index: 622