Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1035 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1543. Min Act: -0.0000

Data Index: 530975 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1535. Min Act: -0.0000

Data Index: 447145 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1536. Min Act: -0.0000

Data Index: 580336 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1231818 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1522. Min Act: -0.0000

Data Index: 858040 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1462. Min Act: -0.0000

Data Index: 627211 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1503. Min Act: -0.0000

Data Index: 714594 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1190262 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1313237 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1442. Min Act: -0.0000

Data Index: 809603 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1415. Min Act: -0.0000

Data Index: 731244 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1351. Min Act: -0.0000

Data Index: 268750 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1396. Min Act: -0.0000

Data Index: 56694 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1022152 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1338. Min Act: -0.0000

Data Index: 742360 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1378. Min Act: -0.0000

Data Index: 553302 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1313. Min Act: -0.0000

Data Index: 437277 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1315. Min Act: -0.0000

Data Index: 91208 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1398. Min Act: -0.0000

Data Index: 885636 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1403. Min Act: -0.0000

Data Index: 260082 (C4 (Web Text))

Max Activating Token Index: 842