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

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

Neuron 1420 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: 0.2105. Min Range: -0.2105

Max Act: 0.2105. Min Act: -0.0001

Data Index: 13635 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1241925 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1712. Min Act: -0.0001

Data Index: 444007 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1701. Min Act: -0.0000

Data Index: 291378 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1608. Min Act: -0.0000

Data Index: 889031 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1584. Min Act: -0.0000

Data Index: 745485 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1499. Min Act: -0.0000

Data Index: 782503 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1263912 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1230146 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1028299 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1378. Min Act: -0.0000

Data Index: 490539 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1125639 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1401. Min Act: -0.0000

Data Index: 693079 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1154983 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1195788 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1305. Min Act: -0.0000

Data Index: 459916 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1239062 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1260. Min Act: -0.0000

Data Index: 88020 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1267. Min Act: -0.0000

Data Index: 675336 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1177117 (C4 (Web Text))

Max Activating Token Index: 538