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

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

Neuron 4511 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: 0.3544. Min Range: -0.3544

Max Act: 0.3544. Min Act: -0.0000

Data Index: 501128 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3198. Min Act: -0.0000

Data Index: 407240 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2855. Min Act: -0.0000

Data Index: 989713 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2606. Min Act: -0.0000

Data Index: 501753 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1072503 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2411. Min Act: -0.0000

Data Index: 750802 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2297. Min Act: -0.0000

Data Index: 795555 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1584059 (Python Code)

Max Activating Token Index: 251

Text #8

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1634565 (Python Code)

Max Activating Token Index: 784

Text #9

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1641568 (Python Code)

Max Activating Token Index: 292

Text #10

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2270. Min Act: -0.0000

Data Index: 331965 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2105. Min Act: -0.0000

Data Index: 815516 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2301. Min Act: -0.0000

Data Index: 349606 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2050. Min Act: -0.0000

Data Index: 565860 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1210661 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1429188 (Python Code)

Max Activating Token Index: 274

Text #16

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1378756 (Python Code)

Max Activating Token Index: 422

Text #17

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1569801 (Python Code)

Max Activating Token Index: 1021

Text #18

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1460287 (Python Code)

Max Activating Token Index: 995

Text #19

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1514991 (Python Code)

Max Activating Token Index: 466