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

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

Neuron 2476 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: 6.1307. Min Range: -6.1307

Max Act: 6.1307. Min Act: -0.0000

Data Index: 1626777 (Python Code)

Max Activating Token Index: 747

Text #1

Max Range: 6.1307. Min Range: -6.1307

Max Act: 6.0288. Min Act: -0.0000

Data Index: 1433457 (Python Code)

Max Activating Token Index: 404

Text #2

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.8604. Min Act: -0.0000

Data Index: 1473151 (Python Code)

Max Activating Token Index: 225

Text #3

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.6174. Min Act: -0.0000

Data Index: 1366032 (Python Code)

Max Activating Token Index: 565

Text #4

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.2708. Min Act: -0.0000

Data Index: 1406516 (Python Code)

Max Activating Token Index: 453

Text #5

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.4149. Min Act: -0.0000

Data Index: 1587333 (Python Code)

Max Activating Token Index: 139

Text #6

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.3837. Min Act: -0.0000

Data Index: 1399223 (Python Code)

Max Activating Token Index: 357

Text #7

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.3628. Min Act: -0.0000

Data Index: 1472128 (Python Code)

Max Activating Token Index: 683

Text #8

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.3313. Min Act: -0.0000

Data Index: 1584733 (Python Code)

Max Activating Token Index: 715

Text #9

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.3503. Min Act: -0.0000

Data Index: 1458670 (Python Code)

Max Activating Token Index: 112

Text #10

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.4797. Min Act: -0.0000

Data Index: 1576807 (Python Code)

Max Activating Token Index: 167

Text #11

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.0674. Min Act: -0.0000

Data Index: 1637527 (Python Code)

Max Activating Token Index: 872

Text #12

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.4299. Min Act: -0.0000

Data Index: 1365838 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.3629. Min Act: -0.0000

Data Index: 1383785 (Python Code)

Max Activating Token Index: 679

Text #14

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.2124. Min Act: -0.0000

Data Index: 1517271 (Python Code)

Max Activating Token Index: 118

Text #15

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.1984. Min Act: -0.0000

Data Index: 1527729 (Python Code)

Max Activating Token Index: 573

Text #16

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.0196. Min Act: -0.0000

Data Index: 1621099 (Python Code)

Max Activating Token Index: 562

Text #17

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.7543. Min Act: -0.0000

Data Index: 1637436 (Python Code)

Max Activating Token Index: 779

Text #18

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.1758. Min Act: -0.0000

Data Index: 1415209 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 6.1307. Min Range: -6.1307

Max Act: 5.1142. Min Act: -0.0000

Data Index: 1550041 (Python Code)

Max Activating Token Index: 132