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

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

Neuron 5116 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0234. Min Range: -3.0234

Max Act: 3.0234. Min Act: -0.0000

Data Index: 1506667 (Python Code)

Max Activating Token Index: 947

Text #1

Max Range: 3.0234. Min Range: -3.0234

Max Act: 3.0083. Min Act: -0.0000

Data Index: 1427509 (Python Code)

Max Activating Token Index: 203

Text #2

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.6937. Min Act: -0.0000

Data Index: 1553242 (Python Code)

Max Activating Token Index: 972

Text #3

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.7090. Min Act: 0.0001

Data Index: 1513313 (Python Code)

Max Activating Token Index: 602

Text #4

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.5820. Min Act: 0.0000

Data Index: 1415461 (Python Code)

Max Activating Token Index: 148

Text #5

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.8638. Min Act: -0.0000

Data Index: 1497074 (Python Code)

Max Activating Token Index: 733

Text #6

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.4468. Min Act: -0.0000

Data Index: 1461149 (Python Code)

Max Activating Token Index: 895

Text #7

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.5730. Min Act: 0.0001

Data Index: 1392116 (Python Code)

Max Activating Token Index: 911

Text #8

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.5844. Min Act: 0.0001

Data Index: 1419685 (Python Code)

Max Activating Token Index: 417

Text #9

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.6082. Min Act: -0.0000

Data Index: 1592403 (Python Code)

Max Activating Token Index: 552

Text #10

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.7166. Min Act: -0.0000

Data Index: 1449167 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.5444. Min Act: -0.0000

Data Index: 1513926 (Python Code)

Max Activating Token Index: 350

Text #12

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.3966. Min Act: -0.0000

Data Index: 1517678 (Python Code)

Max Activating Token Index: 35

Text #13

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.5297. Min Act: -0.0000

Data Index: 1625304 (Python Code)

Max Activating Token Index: 550

Text #14

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.5202. Min Act: -0.0000

Data Index: 1437661 (Python Code)

Max Activating Token Index: 676

Text #15

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.5149. Min Act: 0.0001

Data Index: 1540248 (Python Code)

Max Activating Token Index: 364

Text #16

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.5002. Min Act: -0.0000

Data Index: 1393030 (Python Code)

Max Activating Token Index: 250

Text #17

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.4731. Min Act: -0.0000

Data Index: 1503722 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.4523. Min Act: -0.0000

Data Index: 1623643 (Python Code)

Max Activating Token Index: 159

Text #19

Max Range: 3.0234. Min Range: -3.0234

Max Act: 2.4667. Min Act: -0.0001

Data Index: 1584891 (Python Code)

Max Activating Token Index: 715