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

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

Neuron 6041 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0385. Min Act: -0.0000

Data Index: 1590597 (Python Code)

Max Activating Token Index: 483

Text #1

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1573146 (Python Code)

Max Activating Token Index: 776

Text #2

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1438601 (Python Code)

Max Activating Token Index: 554

Text #3

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1558285 (Python Code)

Max Activating Token Index: 280

Text #4

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.7177. Min Act: -0.0000

Data Index: 1397655 (Python Code)

Max Activating Token Index: 206

Text #5

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6694. Min Act: 0.0000

Data Index: 1539441 (Python Code)

Max Activating Token Index: 522

Text #6

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1558818 (Python Code)

Max Activating Token Index: 950

Text #7

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1624135 (Python Code)

Max Activating Token Index: 107

Text #8

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1596291 (Python Code)

Max Activating Token Index: 296

Text #9

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1589350 (Python Code)

Max Activating Token Index: 537

Text #10

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1639888 (Python Code)

Max Activating Token Index: 450

Text #11

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1553084 (Python Code)

Max Activating Token Index: 186

Text #12

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6508. Min Act: -0.0000

Data Index: 1511167 (Python Code)

Max Activating Token Index: 993

Text #13

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1581002 (Python Code)

Max Activating Token Index: 981

Text #14

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1554708 (Python Code)

Max Activating Token Index: 511

Text #15

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6080. Min Act: 0.0000

Data Index: 1558882 (Python Code)

Max Activating Token Index: 496

Text #16

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1368509 (Python Code)

Max Activating Token Index: 410

Text #17

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1569404 (Python Code)

Max Activating Token Index: 250

Text #18

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.5932. Min Act: 0.0000

Data Index: 1448367 (Python Code)

Max Activating Token Index: 622

Text #19

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1481761 (Python Code)

Max Activating Token Index: 538