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

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

Neuron 1452 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1494876 (Python Code)

Max Activating Token Index: 376

Text #1

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1554377 (Python Code)

Max Activating Token Index: 449

Text #2

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.8181. Min Act: -0.0000

Data Index: 840592 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.8261. Min Act: -0.0001

Data Index: 967665 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1647053 (Python Code)

Max Activating Token Index: 548

Text #5

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.8510. Min Act: -0.0001

Data Index: 317661 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.7552. Min Act: -0.0000

Data Index: 62008 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.7515. Min Act: -0.0001

Data Index: 50915 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.7154. Min Act: -0.0000

Data Index: 191190 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1391111 (Python Code)

Max Activating Token Index: 416

Text #10

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1028998 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1365814 (Python Code)

Max Activating Token Index: 706

Text #12

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.7108. Min Act: -0.0000

Data Index: 467192 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.7461. Min Act: -0.0001

Data Index: 948877 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1374580 (Python Code)

Max Activating Token Index: 911

Text #15

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.6400. Min Act: -0.0001

Data Index: 354379 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1584612 (Python Code)

Max Activating Token Index: 611

Text #17

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.6340. Min Act: -0.0000

Data Index: 316984 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.6779. Min Act: -0.0001

Data Index: 527572 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.9468. Min Range: -0.9468

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1101814 (C4 (Web Text))

Max Activating Token Index: 218