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

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

Neuron 3250 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1781. Min Act: -0.0001

Data Index: 313580 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1657. Min Act: -0.0001

Data Index: 912571 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1484. Min Act: -0.0001

Data Index: 873120 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1458. Min Act: -0.0001

Data Index: 136064 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1353. Min Act: -0.0001

Data Index: 97680 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1292559 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1344. Min Act: -0.0001

Data Index: 607648 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1272. Min Act: -0.0001

Data Index: 589443 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1344. Min Act: -0.0001

Data Index: 81183 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1217. Min Act: -0.0001

Data Index: 895256 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1290785 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1247. Min Act: -0.0001

Data Index: 14715 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1322. Min Act: -0.0001

Data Index: 618226 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1353. Min Act: -0.0001

Data Index: 683162 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1055503 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1254. Min Act: -0.0001

Data Index: 922614 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1268. Min Act: -0.0001

Data Index: 62433 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1457278 (Python Code)

Max Activating Token Index: 935

Text #18

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1252. Min Act: -0.0001

Data Index: 363215 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1131. Min Act: -0.0001

Data Index: 551662 (C4 (Web Text))

Max Activating Token Index: 420