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

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

Neuron 3295 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2252. Min Act: -0.0001

Data Index: 354233 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1505. Min Act: -0.0001

Data Index: 33445 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1507. Min Act: -0.0000

Data Index: 307604 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1472. Min Act: -0.0001

Data Index: 289746 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1685. Min Act: -0.0000

Data Index: 155394 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1450. Min Act: -0.0000

Data Index: 904981 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1393. Min Act: -0.0000

Data Index: 771326 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1317. Min Act: -0.0000

Data Index: 526775 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1358. Min Act: -0.0001

Data Index: 235068 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1286797 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1388. Min Act: -0.0001

Data Index: 440190 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1398. Min Act: -0.0000

Data Index: 412889 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1380. Min Act: -0.0001

Data Index: 334693 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1375. Min Act: -0.0001

Data Index: 370061 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1412. Min Act: -0.0000

Data Index: 506868 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1300. Min Act: -0.0001

Data Index: 426364 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1292. Min Act: -0.0001

Data Index: 446799 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1297. Min Act: -0.0001

Data Index: 282879 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1206504 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1309. Min Act: -0.0001

Data Index: 609972 (C4 (Web Text))

Max Activating Token Index: 210