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

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

Neuron 2748 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2949. Min Range: -4.2949

Max Act: 4.2949. Min Act: -0.0000

Data Index: 1636079 (Python Code)

Max Activating Token Index: 590

Text #1

Max Range: 4.2949. Min Range: -4.2949

Max Act: 4.2569. Min Act: -0.0000

Data Index: 1423500 (Python Code)

Max Activating Token Index: 852

Text #2

Max Range: 4.2949. Min Range: -4.2949

Max Act: 3.9803. Min Act: -0.0000

Data Index: 1411395 (Python Code)

Max Activating Token Index: 729

Text #3

Max Range: 4.2949. Min Range: -4.2949

Max Act: 3.9535. Min Act: -0.0000

Data Index: 1499579 (Python Code)

Max Activating Token Index: 508

Text #4

Max Range: 4.2949. Min Range: -4.2949

Max Act: 3.8929. Min Act: -0.0000

Data Index: 1483727 (Python Code)

Max Activating Token Index: 306

Text #5

Max Range: 4.2949. Min Range: -4.2949

Max Act: 3.5369. Min Act: -0.0000

Data Index: 1630838 (Python Code)

Max Activating Token Index: 568

Text #6

Max Range: 4.2949. Min Range: -4.2949

Max Act: 3.6592. Min Act: -0.0000

Data Index: 1390371 (Python Code)

Max Activating Token Index: 894

Text #7

Max Range: 4.2949. Min Range: -4.2949

Max Act: 3.4213. Min Act: -0.0000

Data Index: 1581201 (Python Code)

Max Activating Token Index: 452

Text #8

Max Range: 4.2949. Min Range: -4.2949

Max Act: 3.1903. Min Act: -0.0000

Data Index: 1479635 (Python Code)

Max Activating Token Index: 690

Text #9

Max Range: 4.2949. Min Range: -4.2949

Max Act: 3.2811. Min Act: -0.0000

Data Index: 1471218 (Python Code)

Max Activating Token Index: 438

Text #10

Max Range: 4.2949. Min Range: -4.2949

Max Act: 3.2936. Min Act: -0.0000

Data Index: 1572531 (Python Code)

Max Activating Token Index: 644

Text #11

Max Range: 4.2949. Min Range: -4.2949

Max Act: 3.1391. Min Act: -0.0000

Data Index: 1478888 (Python Code)

Max Activating Token Index: 237

Text #12

Max Range: 4.2949. Min Range: -4.2949

Max Act: 2.8203. Min Act: -0.0000

Data Index: 1494089 (Python Code)

Max Activating Token Index: 273

Text #13

Max Range: 4.2949. Min Range: -4.2949

Max Act: 2.9067. Min Act: -0.0000

Data Index: 1627933 (Python Code)

Max Activating Token Index: 1020

Text #14

Max Range: 4.2949. Min Range: -4.2949

Max Act: 2.6451. Min Act: -0.0000

Data Index: 1476549 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 4.2949. Min Range: -4.2949

Max Act: 2.7279. Min Act: -0.0000

Data Index: 1369995 (Python Code)

Max Activating Token Index: 42

Text #16

Max Range: 4.2949. Min Range: -4.2949

Max Act: 2.5928. Min Act: -0.0000

Data Index: 1614434 (Python Code)

Max Activating Token Index: 1004

Text #17

Max Range: 4.2949. Min Range: -4.2949

Max Act: 2.8352. Min Act: -0.0000

Data Index: 1600731 (Python Code)

Max Activating Token Index: 474

Text #18

Max Range: 4.2949. Min Range: -4.2949

Max Act: 2.7108. Min Act: -0.0000

Data Index: 1571353 (Python Code)

Max Activating Token Index: 726

Text #19

Max Range: 4.2949. Min Range: -4.2949

Max Act: 2.8169. Min Act: -0.0000

Data Index: 1546495 (Python Code)

Max Activating Token Index: 698