Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3216 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.8500. Min Act: -0.0001

Data Index: 448307 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.8475. Min Act: -0.0001

Data Index: 1354452 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.8141. Min Act: -0.0001

Data Index: 292685 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7877. Min Act: -0.0001

Data Index: 88415 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7915. Min Act: -0.0001

Data Index: 1123009 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7760. Min Act: -0.0001

Data Index: 1243177 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.8053. Min Act: -0.0001

Data Index: 579596 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7494. Min Act: -0.0001

Data Index: 1059898 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7376. Min Act: -0.0001

Data Index: 546472 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7614. Min Act: -0.0001

Data Index: 406095 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7600. Min Act: -0.0001

Data Index: 704851 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7579. Min Act: -0.0001

Data Index: 511591 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7717. Min Act: -0.0001

Data Index: 941075 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7271. Min Act: -0.0001

Data Index: 907262 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7511. Min Act: -0.0001

Data Index: 540834 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7444. Min Act: -0.0001

Data Index: 717350 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7465. Min Act: -0.0001

Data Index: 464881 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7475. Min Act: -0.0001

Data Index: 1289297 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7388. Min Act: -0.0001

Data Index: 588371 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.8500. Min Range: -0.8500

Max Act: 0.7562. Min Act: -0.0001

Data Index: 1159111 (C4 (Web Text))

Max Activating Token Index: 625