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

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

Neuron 876 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.3505. Min Act: -0.0000

Data Index: 696008 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.4755. Min Act: -0.0000

Data Index: 1173798 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.4393. Min Act: -0.0000

Data Index: 131852 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.5750. Min Act: -0.0000

Data Index: 460344 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.4350. Min Act: -0.0000

Data Index: 1292390 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.5675. Min Act: -0.0000

Data Index: 776274 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.5690. Min Act: -0.0000

Data Index: 845635 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.2904. Min Act: -0.0000

Data Index: 296355 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.2759. Min Act: -0.0000

Data Index: 981730 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.4537. Min Act: -0.0000

Data Index: 704860 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.5915. Min Act: -0.0000

Data Index: 181030 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.4637. Min Act: -0.0000

Data Index: 223532 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.5274. Min Act: -0.0000

Data Index: 558606 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.3270. Min Act: -0.0000

Data Index: 471157 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.5503. Min Act: -0.0000

Data Index: 808707 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.6727. Min Act: -0.0000

Data Index: 422182 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.4034. Min Act: -0.0000

Data Index: 115766 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.4000. Min Act: -0.0000

Data Index: 699494 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.2898. Min Act: -0.0000

Data Index: 1271734 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 2.6727. Min Range: -2.6727

Max Act: 2.4005. Min Act: -0.0000

Data Index: 502640 (C4 (Web Text))

Max Activating Token Index: 707