Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 27 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1128301 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1061618 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0579. Min Act: -0.0002

Data Index: 57716 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0571. Min Act: -0.0002

Data Index: 785879 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0572. Min Act: -0.0002

Data Index: 980998 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0558. Min Act: -0.0002

Data Index: 882103 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0530. Min Act: -0.0002

Data Index: 647399 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0560. Min Act: -0.0002

Data Index: 162616 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1296670 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0542. Min Act: -0.0002

Data Index: 290131 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0532. Min Act: -0.0002

Data Index: 72059 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0517. Min Act: -0.0002

Data Index: 987423 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0527. Min Act: -0.0002

Data Index: 491790 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0521. Min Act: -0.0002

Data Index: 118510 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0518. Min Act: -0.0002

Data Index: 51208 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0522. Min Act: -0.0002

Data Index: 306459 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0530. Min Act: -0.0002

Data Index: 227657 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1134715 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0500. Min Act: -0.0002

Data Index: 893411 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0511. Min Act: -0.0002

Data Index: 378482 (C4 (Web Text))

Max Activating Token Index: 983