Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1050 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3385. Min Range: -1.3385

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1278769 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 1.3385. Min Range: -1.3385

Max Act: 1.2235. Min Act: -0.0000

Data Index: 821249 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 1.3385. Min Range: -1.3385

Max Act: 1.0896. Min Act: -0.0000

Data Index: 608549 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9616. Min Act: -0.0000

Data Index: 608127 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9910. Min Act: -0.0000

Data Index: 509214 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9537. Min Act: -0.0000

Data Index: 191702 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9463. Min Act: -0.0000

Data Index: 11760 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9847. Min Act: -0.0000

Data Index: 473112 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9126. Min Act: -0.0000

Data Index: 256140 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9522. Min Act: -0.0000

Data Index: 856078 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8925. Min Act: -0.0000

Data Index: 470495 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1059564 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8518. Min Act: -0.0000

Data Index: 847104 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1061590 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8957. Min Act: -0.0000

Data Index: 764787 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8492. Min Act: -0.0000

Data Index: 705819 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8370. Min Act: -0.0000

Data Index: 439178 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.7776. Min Act: -0.0000

Data Index: 677384 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1016137 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 1.3385. Min Range: -1.3385

Max Act: 0.8763. Min Act: -0.0000

Data Index: 1319708 (C4 (Web Text))

Max Activating Token Index: 322