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

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

Neuron 1305 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.5306. Min Act: -0.0001

Data Index: 1389597 (Python Code)

Max Activating Token Index: 409

Text #1

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.3795. Min Act: -0.0001

Data Index: 151526 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.4569. Min Act: -0.0001

Data Index: 413058 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.3890. Min Act: -0.0001

Data Index: 150166 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.3617. Min Act: -0.0001

Data Index: 1113792 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.2780. Min Act: -0.0000

Data Index: 1542951 (Python Code)

Max Activating Token Index: 756

Text #6

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.2216. Min Act: -0.0001

Data Index: 866450 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.3886. Min Act: -0.0001

Data Index: 1185121 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.3173. Min Act: -0.0001

Data Index: 500661 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.4035. Min Act: -0.0001

Data Index: 1317642 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.2454. Min Act: -0.0001

Data Index: 568720 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.2634. Min Act: -0.0001

Data Index: 1001829 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.2970. Min Act: -0.0001

Data Index: 986354 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.2470. Min Act: -0.0001

Data Index: 1639609 (Python Code)

Max Activating Token Index: 322

Text #14

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.2506. Min Act: -0.0001

Data Index: 240400 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.2698. Min Act: -0.0001

Data Index: 1614001 (Python Code)

Max Activating Token Index: 906

Text #16

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.2661. Min Act: -0.0001

Data Index: 268384 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.2690. Min Act: -0.0001

Data Index: 103230 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.1545. Min Act: -0.0001

Data Index: 38841 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.2181. Min Act: -0.0001

Data Index: 700954 (C4 (Web Text))

Max Activating Token Index: 252