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

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

Neuron 4531 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: 2.3466. Min Range: -2.3466

Max Act: 2.3466. Min Act: -0.0000

Data Index: 1423332 (Python Code)

Max Activating Token Index: 447

Text #1

Max Range: 2.3466. Min Range: -2.3466

Max Act: 2.1753. Min Act: -0.0000

Data Index: 1504759 (Python Code)

Max Activating Token Index: 699

Text #2

Max Range: 2.3466. Min Range: -2.3466

Max Act: 2.0166. Min Act: -0.0000

Data Index: 1624177 (Python Code)

Max Activating Token Index: 785

Text #3

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.8928. Min Act: -0.0000

Data Index: 1613437 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.9800. Min Act: -0.0000

Data Index: 1437168 (Python Code)

Max Activating Token Index: 946

Text #5

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.9528. Min Act: -0.0000

Data Index: 1540060 (Python Code)

Max Activating Token Index: 694

Text #6

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.9208. Min Act: -0.0000

Data Index: 1571415 (Python Code)

Max Activating Token Index: 963

Text #7

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.9049. Min Act: -0.0000

Data Index: 1522760 (Python Code)

Max Activating Token Index: 237

Text #8

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.8984. Min Act: -0.0000

Data Index: 1430865 (Python Code)

Max Activating Token Index: 266

Text #9

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.9516. Min Act: -0.0000

Data Index: 1642091 (Python Code)

Max Activating Token Index: 454

Text #10

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.8335. Min Act: -0.0000

Data Index: 1394918 (Python Code)

Max Activating Token Index: 398

Text #11

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.8147. Min Act: -0.0000

Data Index: 1617018 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.8048. Min Act: -0.0000

Data Index: 1503340 (Python Code)

Max Activating Token Index: 457

Text #13

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.7099. Min Act: -0.0000

Data Index: 1440490 (Python Code)

Max Activating Token Index: 531

Text #14

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.7886. Min Act: -0.0000

Data Index: 1540046 (Python Code)

Max Activating Token Index: 415

Text #15

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.7477. Min Act: -0.0000

Data Index: 1396212 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.7202. Min Act: -0.0000

Data Index: 1378925 (Python Code)

Max Activating Token Index: 345

Text #17

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.8203. Min Act: -0.0000

Data Index: 1553952 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.6741. Min Act: -0.0000

Data Index: 1423337 (Python Code)

Max Activating Token Index: 110

Text #19

Max Range: 2.3466. Min Range: -2.3466

Max Act: 1.6290. Min Act: -0.0000

Data Index: 1453755 (Python Code)

Max Activating Token Index: 102