Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1992 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.6480. Min Act: -0.0001

Data Index: 1484322 (Python Code)

Max Activating Token Index: 485

Text #1

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1496802 (Python Code)

Max Activating Token Index: 535

Text #2

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1603098 (Python Code)

Max Activating Token Index: 379

Text #3

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1364925 (Python Code)

Max Activating Token Index: 305

Text #4

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.4847. Min Act: -0.0001

Data Index: 1545624 (Python Code)

Max Activating Token Index: 792

Text #5

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.5342. Min Act: -0.0001

Data Index: 1518424 (Python Code)

Max Activating Token Index: 719

Text #6

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1615833 (Python Code)

Max Activating Token Index: 593

Text #7

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.5100. Min Act: -0.0001

Data Index: 1552733 (Python Code)

Max Activating Token Index: 640

Text #8

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.5078. Min Act: -0.0001

Data Index: 1437437 (Python Code)

Max Activating Token Index: 958

Text #9

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1623684 (Python Code)

Max Activating Token Index: 693

Text #10

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.4777. Min Act: -0.0001

Data Index: 1387565 (Python Code)

Max Activating Token Index: 140

Text #11

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1415978 (Python Code)

Max Activating Token Index: 795

Text #12

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.4772. Min Act: -0.0001

Data Index: 1374334 (Python Code)

Max Activating Token Index: 879

Text #13

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.5094. Min Act: -0.0001

Data Index: 1630802 (Python Code)

Max Activating Token Index: 731

Text #14

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1504460 (Python Code)

Max Activating Token Index: 381

Text #15

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.4979. Min Act: -0.0001

Data Index: 1391824 (Python Code)

Max Activating Token Index: 418

Text #16

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1422346 (Python Code)

Max Activating Token Index: 719

Text #17

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1567605 (Python Code)

Max Activating Token Index: 724

Text #18

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.4699. Min Act: -0.0001

Data Index: 1574682 (Python Code)

Max Activating Token Index: 873

Text #19

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.5030. Min Act: -0.0001

Data Index: 1598499 (Python Code)

Max Activating Token Index: 113