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

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

Neuron 874 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: 1.9661. Min Range: -1.9661

Max Act: 1.9661. Min Act: -0.0002

Data Index: 79039 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.8169. Min Act: -0.0002

Data Index: 1268966 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.8604. Min Act: -0.0002

Data Index: 493616 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.8033. Min Act: -0.0002

Data Index: 687430 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.9034. Min Act: -0.0002

Data Index: 721716 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.7711. Min Act: -0.0002

Data Index: 238993 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.8528. Min Act: -0.0002

Data Index: 749558 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.7424. Min Act: -0.0002

Data Index: 684701 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.6475. Min Act: -0.0002

Data Index: 723787 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.8425. Min Act: -0.0002

Data Index: 187660 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.6975. Min Act: -0.0002

Data Index: 634872 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.7241. Min Act: -0.0002

Data Index: 830841 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.8176. Min Act: -0.0002

Data Index: 110618 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.6528. Min Act: -0.0002

Data Index: 78340 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.8452. Min Act: -0.0002

Data Index: 784277 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.6666. Min Act: -0.0002

Data Index: 183161 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.6446. Min Act: -0.0002

Data Index: 980379 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.6451. Min Act: -0.0002

Data Index: 1164183 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.8307. Min Act: -0.0002

Data Index: 238362 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 1.9661. Min Range: -1.9661

Max Act: 1.6207. Min Act: -0.0002

Data Index: 1005304 (C4 (Web Text))

Max Activating Token Index: 990