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

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

Neuron 4739 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.7433. Min Act: -0.0002

Data Index: 233615 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.7048. Min Act: -0.0002

Data Index: 241315 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6604. Min Act: -0.0002

Data Index: 707143 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6395. Min Act: -0.0002

Data Index: 1279387 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6760. Min Act: -0.0002

Data Index: 399425 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6624. Min Act: -0.0002

Data Index: 584245 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5506. Min Act: -0.0002

Data Index: 1356543 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5870. Min Act: -0.0002

Data Index: 504432 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5773. Min Act: -0.0002

Data Index: 485250 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5882. Min Act: -0.0002

Data Index: 507950 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5366. Min Act: -0.0002

Data Index: 247866 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5784. Min Act: -0.0002

Data Index: 363334 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5786. Min Act: -0.0002

Data Index: 1202536 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5445. Min Act: -0.0002

Data Index: 1111171 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.4631. Min Act: -0.0002

Data Index: 1150062 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5714. Min Act: -0.0002

Data Index: 313238 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5302. Min Act: -0.0002

Data Index: 1192903 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5906. Min Act: -0.0002

Data Index: 106808 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5706. Min Act: -0.0002

Data Index: 1287767 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5684. Min Act: -0.0002

Data Index: 944177 (C4 (Web Text))

Max Activating Token Index: 351