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

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

Neuron 503 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.2436. Min Act: -0.0000

Data Index: 1646259 (Python Code)

Max Activating Token Index: 712

Text #1

Max Range: 3.2436. Min Range: -3.2436

Max Act: 2.6324. Min Act: -0.0000

Data Index: 1396277 (Python Code)

Max Activating Token Index: 859

Text #2

Max Range: 3.2436. Min Range: -3.2436

Max Act: 2.4837. Min Act: -0.0000

Data Index: 1510418 (Python Code)

Max Activating Token Index: 912

Text #3

Max Range: 3.2436. Min Range: -3.2436

Max Act: 2.4811. Min Act: -0.0000

Data Index: 1412381 (Python Code)

Max Activating Token Index: 875

Text #4

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.9509. Min Act: 0.0000

Data Index: 1363980 (Python Code)

Max Activating Token Index: 480

Text #5

Max Range: 3.2436. Min Range: -3.2436

Max Act: 2.1602. Min Act: -0.0000

Data Index: 1495089 (Python Code)

Max Activating Token Index: 594

Text #6

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.7947. Min Act: -0.0000

Data Index: 1366007 (Python Code)

Max Activating Token Index: 825

Text #7

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.7441. Min Act: 0.0000

Data Index: 1134902 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.6105. Min Act: -0.0000

Data Index: 1389500 (Python Code)

Max Activating Token Index: 1018

Text #9

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.6733. Min Act: -0.0000

Data Index: 1516309 (Python Code)

Max Activating Token Index: 508

Text #10

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.6352. Min Act: -0.0000

Data Index: 1395502 (Python Code)

Max Activating Token Index: 824

Text #11

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.5331. Min Act: -0.0000

Data Index: 1596949 (Python Code)

Max Activating Token Index: 714

Text #12

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.6062. Min Act: -0.0000

Data Index: 1458056 (Python Code)

Max Activating Token Index: 164

Text #13

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.3082. Min Act: -0.0000

Data Index: 1561127 (Python Code)

Max Activating Token Index: 858

Text #14

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.3477. Min Act: 0.0000

Data Index: 1454203 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.4748. Min Act: -0.0000

Data Index: 1492989 (Python Code)

Max Activating Token Index: 962

Text #16

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.4586. Min Act: -0.0000

Data Index: 1515167 (Python Code)

Max Activating Token Index: 947

Text #17

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.3868. Min Act: -0.0000

Data Index: 1441299 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.3532. Min Act: -0.0000

Data Index: 1601010 (Python Code)

Max Activating Token Index: 648

Text #19

Max Range: 3.2436. Min Range: -3.2436

Max Act: 1.3128. Min Act: -0.0000

Data Index: 1379715 (Python Code)

Max Activating Token Index: 593