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

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

Neuron 1624 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.7274. Min Act: -0.0000

Data Index: 465309 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.7114. Min Act: -0.0000

Data Index: 167041 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.6484. Min Act: -0.0000

Data Index: 746205 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1622797 (Python Code)

Max Activating Token Index: 439

Text #4

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1131543 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1386526 (Python Code)

Max Activating Token Index: 847

Text #6

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4842. Min Act: -0.0000

Data Index: 909797 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4852. Min Act: -0.0000

Data Index: 358015 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1409564 (Python Code)

Max Activating Token Index: 950

Text #9

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1435870 (Python Code)

Max Activating Token Index: 309

Text #10

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1477705 (Python Code)

Max Activating Token Index: 875

Text #11

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4483. Min Act: -0.0000

Data Index: 195893 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1519846 (Python Code)

Max Activating Token Index: 262

Text #13

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4647. Min Act: -0.0000

Data Index: 310868 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4348. Min Act: -0.0000

Data Index: 840352 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4495. Min Act: -0.0000

Data Index: 720662 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4473. Min Act: -0.0000

Data Index: 343525 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4250. Min Act: -0.0000

Data Index: 130199 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1352583 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1309808 (C4 (Web Text))

Max Activating Token Index: 179