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

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

Neuron 2653 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: 0.2323. Min Range: -0.2323

Max Act: 0.2323. Min Act: -0.0000

Data Index: 517246 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2174. Min Act: -0.0000

Data Index: 64726 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1965. Min Act: -0.0000

Data Index: 811335 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2008. Min Act: -0.0000

Data Index: 93100 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1569823 (Python Code)

Max Activating Token Index: 766

Text #5

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1948. Min Act: -0.0000

Data Index: 987939 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1202335 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1826. Min Act: -0.0000

Data Index: 781223 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1407669 (Python Code)

Max Activating Token Index: 792

Text #9

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1856. Min Act: -0.0000

Data Index: 112541 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1838. Min Act: -0.0000

Data Index: 379390 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1597725 (Python Code)

Max Activating Token Index: 227

Text #12

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1645. Min Act: -0.0000

Data Index: 1076680 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1404361 (Python Code)

Max Activating Token Index: 510

Text #14

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1548368 (Python Code)

Max Activating Token Index: 774

Text #15

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1163486 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1505. Min Act: -0.0000

Data Index: 247043 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1509. Min Act: -0.0000

Data Index: 421268 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1454. Min Act: -0.0000

Data Index: 281903 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1460. Min Act: -0.0000

Data Index: 736214 (C4 (Web Text))

Max Activating Token Index: 984