Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1564 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1877. Min Act: -0.0000

Data Index: 887267 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1963. Min Act: -0.0000

Data Index: 219669 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1605. Min Act: -0.0000

Data Index: 565162 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1047443 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1470. Min Act: -0.0000

Data Index: 363204 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1518. Min Act: -0.0000

Data Index: 352855 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1033751 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1355. Min Act: -0.0000

Data Index: 364733 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1342. Min Act: -0.0000

Data Index: 900759 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1403. Min Act: -0.0000

Data Index: 106344 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1294. Min Act: -0.0000

Data Index: 117031 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1284. Min Act: -0.0000

Data Index: 222683 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1312. Min Act: -0.0000

Data Index: 880032 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1299. Min Act: -0.0000

Data Index: 826410 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1239. Min Act: -0.0000

Data Index: 186807 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1302352 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1260. Min Act: -0.0000

Data Index: 212195 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1248. Min Act: -0.0000

Data Index: 55737 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1209. Min Act: -0.0000

Data Index: 247774 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1118. Min Act: -0.0000

Data Index: 710695 (C4 (Web Text))

Max Activating Token Index: 656