Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 753 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.6235. Min Act: -0.0000

Data Index: 1321819 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5141. Min Act: -0.0000

Data Index: 1103726 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.4582. Min Act: -0.0000

Data Index: 974110 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.4325. Min Act: -0.0000

Data Index: 283732 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.4788. Min Act: -0.0000

Data Index: 1235066 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.4029. Min Act: -0.0000

Data Index: 145274 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.4124. Min Act: -0.0000

Data Index: 583370 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.3349. Min Act: -0.0000

Data Index: 725619 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.3917. Min Act: -0.0000

Data Index: 1117512 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.4050. Min Act: -0.0000

Data Index: 218123 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.3325. Min Act: -0.0000

Data Index: 1568583 (Python Code)

Max Activating Token Index: 555

Text #11

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2760. Min Act: -0.0000

Data Index: 965387 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2235. Min Act: -0.0000

Data Index: 608759 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1192439 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1420956 (Python Code)

Max Activating Token Index: 867

Text #15

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.3955. Min Act: -0.0000

Data Index: 793334 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2356. Min Act: -0.0000

Data Index: 1395038 (Python Code)

Max Activating Token Index: 395

Text #17

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.1924. Min Act: -0.0000

Data Index: 646933 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2628. Min Act: -0.0000

Data Index: 1432484 (Python Code)

Max Activating Token Index: 559

Text #19

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2322. Min Act: -0.0000

Data Index: 649304 (C4 (Web Text))

Max Activating Token Index: 703