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

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

Neuron 2785 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.9145. Min Act: -0.0000

Data Index: 1508040 (Python Code)

Max Activating Token Index: 915

Text #1

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.7472. Min Act: -0.0000

Data Index: 931257 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.7107. Min Act: -0.0000

Data Index: 1461839 (Python Code)

Max Activating Token Index: 521

Text #3

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.7692. Min Act: -0.0000

Data Index: 1560594 (Python Code)

Max Activating Token Index: 789

Text #4

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.6487. Min Act: -0.0000

Data Index: 1610313 (Python Code)

Max Activating Token Index: 126

Text #5

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.9716. Min Act: -0.0000

Data Index: 1644253 (Python Code)

Max Activating Token Index: 316

Text #6

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.8344. Min Act: -0.0000

Data Index: 1610548 (Python Code)

Max Activating Token Index: 596

Text #7

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.6528. Min Act: -0.0000

Data Index: 1399787 (Python Code)

Max Activating Token Index: 969

Text #8

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.8852. Min Act: -0.0000

Data Index: 1464200 (Python Code)

Max Activating Token Index: 316

Text #9

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.5946. Min Act: -0.0000

Data Index: 1383374 (Python Code)

Max Activating Token Index: 419

Text #10

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.4049. Min Act: -0.0000

Data Index: 1588081 (Python Code)

Max Activating Token Index: 193

Text #11

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.6122. Min Act: -0.0000

Data Index: 1462846 (Python Code)

Max Activating Token Index: 472

Text #12

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.5131. Min Act: -0.0000

Data Index: 1437707 (Python Code)

Max Activating Token Index: 436

Text #13

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.5973. Min Act: -0.0000

Data Index: 1396305 (Python Code)

Max Activating Token Index: 222

Text #14

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.4989. Min Act: -0.0000

Data Index: 1582241 (Python Code)

Max Activating Token Index: 160

Text #15

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.4190. Min Act: -0.0000

Data Index: 1428839 (Python Code)

Max Activating Token Index: 890

Text #16

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.7141. Min Act: -0.0000

Data Index: 1648755 (Python Code)

Max Activating Token Index: 381

Text #17

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1548768 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.4581. Min Act: -0.0000

Data Index: 1396605 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.3071. Min Act: -0.0000

Data Index: 1621174 (Python Code)

Max Activating Token Index: 206