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

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

Neuron 3399 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0448. Min Act: -0.0002

Data Index: 880301 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1128674 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1275304 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0420. Min Act: -0.0002

Data Index: 631023 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0426. Min Act: -0.0002

Data Index: 696771 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0425. Min Act: -0.0002

Data Index: 640120 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1086825 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1167507 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0420. Min Act: -0.0002

Data Index: 122865 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1245043 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1111830 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1283720 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0413. Min Act: -0.0002

Data Index: 650365 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0410. Min Act: -0.0002

Data Index: 310725 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0405. Min Act: -0.0002

Data Index: 411076 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0396. Min Act: -0.0002

Data Index: 799394 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0404. Min Act: -0.0002

Data Index: 47238 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0404. Min Act: -0.0002

Data Index: 941177 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1251466 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1184085 (C4 (Web Text))

Max Activating Token Index: 895