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

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

Neuron 5900 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: 0.4607. Min Range: -0.4607

Max Act: 0.4607. Min Act: -0.0000

Data Index: 700812 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.3032. Min Act: -0.0000

Data Index: 237517 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2754. Min Act: -0.0000

Data Index: 820808 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1207471 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1230389 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2692. Min Act: -0.0000

Data Index: 358575 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2573. Min Act: -0.0000

Data Index: 495002 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2602. Min Act: -0.0000

Data Index: 717266 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1207238 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2366. Min Act: -0.0000

Data Index: 352826 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2591. Min Act: -0.0000

Data Index: 308650 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1058455 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2272. Min Act: -0.0000

Data Index: 61426 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2419. Min Act: -0.0000

Data Index: 585428 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2252. Min Act: -0.0000

Data Index: 720962 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2426. Min Act: -0.0000

Data Index: 485429 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2408. Min Act: -0.0000

Data Index: 772158 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2230. Min Act: -0.0000

Data Index: 942219 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2225. Min Act: -0.0000

Data Index: 243203 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.2430. Min Act: -0.0000

Data Index: 215676 (C4 (Web Text))

Max Activating Token Index: 709