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

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

Neuron 768 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1498944 (Python Code)

Max Activating Token Index: 329

Text #1

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1525. Min Act: -0.0001

Data Index: 918592 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1370877 (Python Code)

Max Activating Token Index: 708

Text #3

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1488224 (Python Code)

Max Activating Token Index: 647

Text #4

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1557771 (Python Code)

Max Activating Token Index: 399

Text #5

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1500699 (Python Code)

Max Activating Token Index: 691

Text #6

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1488. Min Act: -0.0001

Data Index: 1585537 (Python Code)

Max Activating Token Index: 639

Text #7

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1460538 (Python Code)

Max Activating Token Index: 707

Text #8

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1642283 (Python Code)

Max Activating Token Index: 853

Text #9

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1384378 (Python Code)

Max Activating Token Index: 89

Text #10

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1630016 (Python Code)

Max Activating Token Index: 70

Text #11

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1417. Min Act: -0.0001

Data Index: 1446885 (Python Code)

Max Activating Token Index: 618

Text #12

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1497979 (Python Code)

Max Activating Token Index: 817

Text #13

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1463209 (Python Code)

Max Activating Token Index: 103

Text #14

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1341. Min Act: -0.0001

Data Index: 160368 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1425. Min Act: -0.0001

Data Index: 1513967 (Python Code)

Max Activating Token Index: 901

Text #16

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1364634 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1420181 (Python Code)

Max Activating Token Index: 702

Text #18

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1593537 (Python Code)

Max Activating Token Index: 55

Text #19

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1472382 (Python Code)

Max Activating Token Index: 854