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

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

Neuron 1084 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: 0.9495. Min Range: -0.9495

Max Act: 0.9495. Min Act: -0.0001

Data Index: 1370878 (Python Code)

Max Activating Token Index: 195

Text #1

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.6818. Min Act: -0.0001

Data Index: 1391594 (Python Code)

Max Activating Token Index: 650

Text #2

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.3474. Min Act: -0.0001

Data Index: 1530823 (Python Code)

Max Activating Token Index: 50

Text #3

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.1690. Min Act: -0.0001

Data Index: 1376932 (Python Code)

Max Activating Token Index: 143

Text #4

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.1929. Min Act: -0.0001

Data Index: 1613389 (Python Code)

Max Activating Token Index: 267

Text #5

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.1508. Min Act: -0.0001

Data Index: 683180 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1510667 (Python Code)

Max Activating Token Index: 553

Text #7

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.1290. Min Act: -0.0000

Data Index: 41588 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1508620 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1512339 (Python Code)

Max Activating Token Index: 472

Text #10

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.0820. Min Act: -0.0001

Data Index: 768510 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.0703. Min Act: -0.0001

Data Index: 1655653 (Python Code)

Max Activating Token Index: 189

Text #12

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.0690. Min Act: -0.0001

Data Index: 462361 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1553849 (Python Code)

Max Activating Token Index: 441

Text #14

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.0702. Min Act: -0.0001

Data Index: 916053 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.0750. Min Act: -0.0001

Data Index: 585481 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.0637. Min Act: -0.0001

Data Index: 1463355 (Python Code)

Max Activating Token Index: 624

Text #17

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.0597. Min Act: -0.0001

Data Index: 699430 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.0713. Min Act: -0.0001

Data Index: 808927 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.0841. Min Act: -0.0001

Data Index: 474799 (C4 (Web Text))

Max Activating Token Index: 775