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

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

Neuron 4104 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1994. Min Act: -0.0001

Data Index: 520768 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1827. Min Act: -0.0001

Data Index: 763362 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1634. Min Act: -0.0001

Data Index: 113047 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1604. Min Act: -0.0001

Data Index: 1099800 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1608. Min Act: -0.0001

Data Index: 951603 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1437. Min Act: -0.0001

Data Index: 931528 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1552. Min Act: -0.0001

Data Index: 859599 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1536. Min Act: -0.0001

Data Index: 408046 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1483. Min Act: -0.0001

Data Index: 662494 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1529. Min Act: -0.0001

Data Index: 670171 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1520. Min Act: -0.0001

Data Index: 445183 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1470. Min Act: -0.0001

Data Index: 111829 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1419. Min Act: -0.0001

Data Index: 1103368 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1386. Min Act: -0.0001

Data Index: 298807 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1322. Min Act: -0.0001

Data Index: 115786 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1336. Min Act: -0.0001

Data Index: 73036 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1283. Min Act: -0.0001

Data Index: 5913 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1267. Min Act: -0.0001

Data Index: 344911 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1302. Min Act: -0.0001

Data Index: 685729 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1248150 (C4 (Web Text))

Max Activating Token Index: 859