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

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

Neuron 3168 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1908. Min Act: -0.0000

Data Index: 638702 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1807. Min Act: -0.0001

Data Index: 53215 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1619. Min Act: -0.0000

Data Index: 1175244 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1553. Min Act: -0.0000

Data Index: 36301 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1345426 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1521. Min Act: -0.0000

Data Index: 337649 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1439. Min Act: -0.0000

Data Index: 301147 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1065788 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1480. Min Act: -0.0001

Data Index: 50655 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1207823 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1409. Min Act: -0.0001

Data Index: 804975 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1398. Min Act: -0.0000

Data Index: 410827 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1350. Min Act: -0.0000

Data Index: 151377 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1353. Min Act: -0.0000

Data Index: 954062 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1061598 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1317. Min Act: -0.0001

Data Index: 373843 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1319. Min Act: -0.0000

Data Index: 538818 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1053646 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1354. Min Act: -0.0000

Data Index: 259380 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1353. Min Act: -0.0001

Data Index: 1349379 (C4 (Web Text))

Max Activating Token Index: 941