Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 578 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.9147. Min Act: -0.0000

Data Index: 752568 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.9368. Min Act: -0.0000

Data Index: 296774 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8615. Min Act: -0.0000

Data Index: 565587 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8647. Min Act: -0.0000

Data Index: 325223 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8065. Min Act: -0.0000

Data Index: 67719 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8299. Min Act: -0.0000

Data Index: 649395 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1046290 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7677. Min Act: -0.0000

Data Index: 937038 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7615. Min Act: -0.0000

Data Index: 44585 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7827. Min Act: -0.0000

Data Index: 702243 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7609. Min Act: -0.0000

Data Index: 1237566 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7820. Min Act: -0.0001

Data Index: 377823 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8022. Min Act: -0.0000

Data Index: 286596 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7397. Min Act: -0.0000

Data Index: 340788 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1057701 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7212. Min Act: -0.0000

Data Index: 578606 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7670. Min Act: -0.0000

Data Index: 353532 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7205. Min Act: -0.0000

Data Index: 39753 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1320223 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7388. Min Act: -0.0000

Data Index: 381716 (C4 (Web Text))

Max Activating Token Index: 176