Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2518 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0394. Min Act: -0.0001

Data Index: 803492 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0360. Min Act: -0.0001

Data Index: 125196 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0375. Min Act: -0.0001

Data Index: 864441 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1487250 (Python Code)

Max Activating Token Index: 912

Text #4

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1440476 (Python Code)

Max Activating Token Index: 778

Text #5

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0343. Min Act: -0.0001

Data Index: 805886 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0327. Min Act: -0.0001

Data Index: 211312 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1506935 (Python Code)

Max Activating Token Index: 416

Text #8

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1490247 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1527448 (Python Code)

Max Activating Token Index: 579

Text #10

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0297. Min Act: -0.0001

Data Index: 1454030 (Python Code)

Max Activating Token Index: 918

Text #11

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1417791 (Python Code)

Max Activating Token Index: 955

Text #12

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0301. Min Act: -0.0001

Data Index: 1650964 (Python Code)

Max Activating Token Index: 595

Text #13

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0307. Min Act: -0.0001

Data Index: 1625709 (Python Code)

Max Activating Token Index: 604

Text #14

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1485164 (Python Code)

Max Activating Token Index: 584

Text #15

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0287. Min Act: -0.0001

Data Index: 1610671 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1632977 (Python Code)

Max Activating Token Index: 720

Text #17

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0281. Min Act: -0.0001

Data Index: 687790 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1431785 (Python Code)

Max Activating Token Index: 1012

Text #19

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1414188 (Python Code)

Max Activating Token Index: 1009