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

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

Neuron 4697 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: 2.3403. Min Range: -2.3403

Max Act: 2.3403. Min Act: -0.0000

Data Index: 249327 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 2.3403. Min Range: -2.3403

Max Act: 2.0954. Min Act: -0.0000

Data Index: 351734 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 2.3403. Min Range: -2.3403

Max Act: 2.0107. Min Act: -0.0000

Data Index: 526831 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.7625. Min Act: -0.0000

Data Index: 1078340 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.7040. Min Act: -0.0000

Data Index: 856039 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.6908. Min Act: -0.0000

Data Index: 403822 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.7686. Min Act: -0.0000

Data Index: 705099 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.6878. Min Act: -0.0000

Data Index: 1416876 (Python Code)

Max Activating Token Index: 376

Text #8

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.5048. Min Act: -0.0000

Data Index: 1045913 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.5031. Min Act: -0.0000

Data Index: 602446 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.6002. Min Act: -0.0000

Data Index: 500469 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.4794. Min Act: -0.0000

Data Index: 1256743 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.4445. Min Act: -0.0000

Data Index: 1526126 (Python Code)

Max Activating Token Index: 170

Text #13

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.4443. Min Act: -0.0000

Data Index: 365175 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.4025. Min Act: -0.0000

Data Index: 1248945 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.3243. Min Act: -0.0000

Data Index: 1208338 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.3937. Min Act: -0.0000

Data Index: 854099 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.4721. Min Act: -0.0000

Data Index: 755580 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.3796. Min Act: -0.0000

Data Index: 957355 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 2.3403. Min Range: -2.3403

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1229609 (C4 (Web Text))

Max Activating Token Index: 253