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

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

Neuron 1943 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0205. Min Range: -4.0205

Max Act: 4.0205. Min Act: -0.0000

Data Index: 1465369 (Python Code)

Max Activating Token Index: 189

Text #1

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.8510. Min Act: -0.0000

Data Index: 1452612 (Python Code)

Max Activating Token Index: 401

Text #2

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.7681. Min Act: -0.0000

Data Index: 1456372 (Python Code)

Max Activating Token Index: 461

Text #3

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.6265. Min Act: -0.0000

Data Index: 1555319 (Python Code)

Max Activating Token Index: 430

Text #4

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.4670. Min Act: -0.0000

Data Index: 1512784 (Python Code)

Max Activating Token Index: 604

Text #5

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.5936. Min Act: -0.0000

Data Index: 1571578 (Python Code)

Max Activating Token Index: 658

Text #6

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.2518. Min Act: -0.0000

Data Index: 1581529 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.5075. Min Act: -0.0000

Data Index: 1409591 (Python Code)

Max Activating Token Index: 608

Text #8

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.2744. Min Act: -0.0000

Data Index: 1399525 (Python Code)

Max Activating Token Index: 732

Text #9

Max Range: 4.0205. Min Range: -4.0205

Max Act: 2.9888. Min Act: -0.0000

Data Index: 1548383 (Python Code)

Max Activating Token Index: 745

Text #10

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.3920. Min Act: -0.0000

Data Index: 1534170 (Python Code)

Max Activating Token Index: 710

Text #11

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.4012. Min Act: -0.0000

Data Index: 1536602 (Python Code)

Max Activating Token Index: 807

Text #12

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.1471. Min Act: -0.0000

Data Index: 1611519 (Python Code)

Max Activating Token Index: 318

Text #13

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.1287. Min Act: -0.0000

Data Index: 1447485 (Python Code)

Max Activating Token Index: 652

Text #14

Max Range: 4.0205. Min Range: -4.0205

Max Act: 2.9542. Min Act: -0.0000

Data Index: 1530991 (Python Code)

Max Activating Token Index: 249

Text #15

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.1043. Min Act: -0.0000

Data Index: 1418398 (Python Code)

Max Activating Token Index: 250

Text #16

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.0520. Min Act: -0.0000

Data Index: 1449957 (Python Code)

Max Activating Token Index: 301

Text #17

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.0250. Min Act: -0.0000

Data Index: 1397505 (Python Code)

Max Activating Token Index: 608

Text #18

Max Range: 4.0205. Min Range: -4.0205

Max Act: 3.0207. Min Act: -0.0000

Data Index: 1581837 (Python Code)

Max Activating Token Index: 440

Text #19

Max Range: 4.0205. Min Range: -4.0205

Max Act: 2.9947. Min Act: -0.0000

Data Index: 1587565 (Python Code)

Max Activating Token Index: 618