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

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

Neuron 1470 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: 0.1629. Min Range: -0.1629

Max Act: 0.1629. Min Act: -0.0000

Data Index: 594947 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1591. Min Act: -0.0000

Data Index: 656617 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1012214 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1582. Min Act: -0.0001

Data Index: 111800 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1485. Min Act: -0.0001

Data Index: 231023 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1260877 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1477. Min Act: -0.0000

Data Index: 56196 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1402. Min Act: -0.0000

Data Index: 445060 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1450. Min Act: -0.0001

Data Index: 159138 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1361. Min Act: -0.0000

Data Index: 854407 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1389. Min Act: -0.0001

Data Index: 82109 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1399215 (Python Code)

Max Activating Token Index: 608

Text #12

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1039. Min Act: -0.0001

Data Index: 240808 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1378. Min Act: -0.0001

Data Index: 1653771 (Python Code)

Max Activating Token Index: 964

Text #14

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1323. Min Act: -0.0001

Data Index: 58598 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1419. Min Act: -0.0000

Data Index: 487973 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1377361 (Python Code)

Max Activating Token Index: 321

Text #17

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1261. Min Act: -0.0001

Data Index: 870807 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1203. Min Act: -0.0000

Data Index: 12929 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.1629. Min Range: -0.1629

Max Act: 0.1246. Min Act: -0.0001

Data Index: 116881 (C4 (Web Text))

Max Activating Token Index: 83