Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3890 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1862. Min Act: -0.0000

Data Index: 502419 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1820. Min Act: -0.0000

Data Index: 586472 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1717. Min Act: -0.0000

Data Index: 897355 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1044524 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1651. Min Act: -0.0000

Data Index: 852517 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1400. Min Act: -0.0000

Data Index: 263683 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1396. Min Act: -0.0000

Data Index: 381751 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1408. Min Act: -0.0000

Data Index: 167079 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1291. Min Act: -0.0000

Data Index: 419497 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1062. Min Act: -0.0000

Data Index: 421102 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1406. Min Act: -0.0000

Data Index: 203653 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1355. Min Act: -0.0000

Data Index: 267177 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1000447 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1329. Min Act: -0.0000

Data Index: 447759 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1299. Min Act: -0.0000

Data Index: 1374772 (Python Code)

Max Activating Token Index: 935

Text #15

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1438. Min Act: -0.0000

Data Index: 166511 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1321036 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1319. Min Act: -0.0000

Data Index: 113971 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1376. Min Act: -0.0000

Data Index: 635042 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1195. Min Act: -0.0000

Data Index: 595489 (C4 (Web Text))

Max Activating Token Index: 91