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

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

Neuron 1803 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: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0002

Data Index: 165598 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1316019 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0499. Min Act: -0.0002

Data Index: 956433 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0522. Min Act: -0.0002

Data Index: 557765 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1274854 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1242288 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0457. Min Act: -0.0002

Data Index: 129933 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0421. Min Act: -0.0002

Data Index: 285087 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0397. Min Act: -0.0002

Data Index: 434885 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0392. Min Act: -0.0002

Data Index: 318291 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0377. Min Act: -0.0002

Data Index: 441282 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1118709 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0394. Min Act: -0.0002

Data Index: 302405 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0399. Min Act: -0.0002

Data Index: 603743 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0381. Min Act: -0.0002

Data Index: 47371 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1102423 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0379. Min Act: -0.0002

Data Index: 263916 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0375. Min Act: -0.0002

Data Index: 261169 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0384. Min Act: -0.0002

Data Index: 521266 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0388. Min Act: -0.0002

Data Index: 213859 (C4 (Web Text))

Max Activating Token Index: 310