Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 876 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4365. Min Act: -0.0001

Data Index: 1474410 (Python Code)

Max Activating Token Index: 751

Text #1

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4205. Min Act: -0.0001

Data Index: 1620088 (Python Code)

Max Activating Token Index: 825

Text #2

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3952. Min Act: -0.0001

Data Index: 1619266 (Python Code)

Max Activating Token Index: 727

Text #3

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3906. Min Act: -0.0001

Data Index: 1365249 (Python Code)

Max Activating Token Index: 987

Text #4

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3440. Min Act: -0.0001

Data Index: 1361986 (Python Code)

Max Activating Token Index: 653

Text #5

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3740. Min Act: -0.0001

Data Index: 1579161 (Python Code)

Max Activating Token Index: 523

Text #6

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3544. Min Act: -0.0001

Data Index: 1600346 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3420. Min Act: -0.0001

Data Index: 1277733 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1619788 (Python Code)

Max Activating Token Index: 816

Text #9

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1576404 (Python Code)

Max Activating Token Index: 69

Text #10

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3195. Min Act: -0.0001

Data Index: 1472149 (Python Code)

Max Activating Token Index: 925

Text #11

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1521492 (Python Code)

Max Activating Token Index: 255

Text #12

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3079. Min Act: -0.0001

Data Index: 1530109 (Python Code)

Max Activating Token Index: 627

Text #13

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1486269 (Python Code)

Max Activating Token Index: 395

Text #14

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3173. Min Act: -0.0001

Data Index: 1411225 (Python Code)

Max Activating Token Index: 180

Text #15

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3346. Min Act: -0.0001

Data Index: 1447808 (Python Code)

Max Activating Token Index: 1000

Text #16

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3254. Min Act: -0.0001

Data Index: 1442657 (Python Code)

Max Activating Token Index: 517

Text #17

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3442. Min Act: -0.0000

Data Index: 234368 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3087. Min Act: -0.0001

Data Index: 1486663 (Python Code)

Max Activating Token Index: 733

Text #19

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3065. Min Act: -0.0000

Data Index: 665546 (C4 (Web Text))

Max Activating Token Index: 726