Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2732 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.6297. Min Act: -0.0000

Data Index: 411099 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1214944 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1631619 (Python Code)

Max Activating Token Index: 851

Text #3

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5842. Min Act: -0.0000

Data Index: 430539 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1486449 (Python Code)

Max Activating Token Index: 943

Text #5

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.6131. Min Act: -0.0000

Data Index: 77373 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1261465 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1407404 (Python Code)

Max Activating Token Index: 1010

Text #8

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1632066 (Python Code)

Max Activating Token Index: 370

Text #9

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1478906 (Python Code)

Max Activating Token Index: 593

Text #10

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1435975 (Python Code)

Max Activating Token Index: 481

Text #11

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1096976 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1617592 (Python Code)

Max Activating Token Index: 197

Text #13

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5444. Min Act: -0.0000

Data Index: 226816 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5171. Min Act: -0.0000

Data Index: 64305 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.4996. Min Act: -0.0000

Data Index: 734697 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5204. Min Act: -0.0000

Data Index: 623323 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5083. Min Act: -0.0000

Data Index: 305620 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1046216 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1620574 (Python Code)

Max Activating Token Index: 477