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

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

Neuron 1690 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: 1.5038. Min Range: -1.5038

Max Act: 1.5038. Min Act: -0.0001

Data Index: 1458371 (Python Code)

Max Activating Token Index: 566

Text #1

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.3190. Min Act: -0.0001

Data Index: 1078062 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2238. Min Act: -0.0001

Data Index: 1116879 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2154. Min Act: -0.0001

Data Index: 980717 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2124. Min Act: -0.0001

Data Index: 1590902 (Python Code)

Max Activating Token Index: 700

Text #5

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.1102. Min Act: -0.0001

Data Index: 1295215 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.0887. Min Act: -0.0001

Data Index: 233114 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.1151. Min Act: -0.0001

Data Index: 957453 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.0755. Min Act: -0.0001

Data Index: 42467 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.0415. Min Act: -0.0001

Data Index: 593390 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2507. Min Act: -0.0001

Data Index: 981735 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 1.5038. Min Range: -1.5038

Max Act: 0.9531. Min Act: -0.0001

Data Index: 766985 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 1.5038. Min Range: -1.5038

Max Act: 0.9965. Min Act: -0.0001

Data Index: 655465 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.0494. Min Act: -0.0001

Data Index: 393988 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 1.5038. Min Range: -1.5038

Max Act: 0.9926. Min Act: -0.0001

Data Index: 903982 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.5038. Min Range: -1.5038

Max Act: 0.9524. Min Act: -0.0001

Data Index: 1307799 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 1.5038. Min Range: -1.5038

Max Act: 0.9152. Min Act: -0.0001

Data Index: 40135 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 1.5038. Min Range: -1.5038

Max Act: 0.8718. Min Act: -0.0001

Data Index: 1033763 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 1.5038. Min Range: -1.5038

Max Act: 0.8341. Min Act: -0.0001

Data Index: 694157 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 1.5038. Min Range: -1.5038

Max Act: 0.8650. Min Act: -0.0001

Data Index: 17549 (C4 (Web Text))

Max Activating Token Index: 797