Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4340 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2408. Min Act: -0.0002

Data Index: 1179035 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1994. Min Act: -0.0002

Data Index: 576875 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1897. Min Act: -0.0002

Data Index: 397032 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1592. Min Act: -0.0002

Data Index: 1030899 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1630. Min Act: -0.0002

Data Index: 826488 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1621. Min Act: -0.0002

Data Index: 1255195 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1632. Min Act: -0.0002

Data Index: 618012 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1501. Min Act: -0.0002

Data Index: 243757 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1541. Min Act: -0.0002

Data Index: 377303 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1520. Min Act: -0.0002

Data Index: 1143452 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1465. Min Act: -0.0002

Data Index: 1168764 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1510. Min Act: -0.0002

Data Index: 200092 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1418. Min Act: -0.0002

Data Index: 1261704 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1414. Min Act: -0.0002

Data Index: 614612 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1404. Min Act: -0.0002

Data Index: 775042 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1345. Min Act: -0.0002

Data Index: 1174830 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1443. Min Act: -0.0002

Data Index: 1126846 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1333. Min Act: -0.0002

Data Index: 733954 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1409. Min Act: -0.0002

Data Index: 560166 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1331. Min Act: -0.0002

Data Index: 1246301 (C4 (Web Text))

Max Activating Token Index: 357