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

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

Neuron 2159 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.4386. Min Act: -0.0000

Data Index: 709070 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.3718. Min Act: -0.0001

Data Index: 157689 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.2167. Min Act: -0.0001

Data Index: 1460869 (Python Code)

Max Activating Token Index: 952

Text #3

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1346512 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1312724 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1099018 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.4386. Min Range: -1.4386

Max Act: 0.9817. Min Act: -0.0001

Data Index: 1505692 (Python Code)

Max Activating Token Index: 953

Text #7

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.1226. Min Act: -0.0000

Data Index: 341962 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.0625. Min Act: -0.0001

Data Index: 1366801 (Python Code)

Max Activating Token Index: 629

Text #9

Max Range: 1.4386. Min Range: -1.4386

Max Act: 0.9885. Min Act: -0.0001

Data Index: 1177901 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.1146. Min Act: -0.0001

Data Index: 1096886 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.1472. Min Act: -0.0001

Data Index: 1329119 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.0254. Min Act: -0.0000

Data Index: 751336 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.0139. Min Act: -0.0001

Data Index: 1554339 (Python Code)

Max Activating Token Index: 555

Text #14

Max Range: 1.4386. Min Range: -1.4386

Max Act: 0.9764. Min Act: -0.0001

Data Index: 54561 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 1.4386. Min Range: -1.4386

Max Act: 1.0351. Min Act: -0.0001

Data Index: 1403691 (Python Code)

Max Activating Token Index: 927

Text #16

Max Range: 1.4386. Min Range: -1.4386

Max Act: 0.9348. Min Act: -0.0001

Data Index: 1537523 (Python Code)

Max Activating Token Index: 782

Text #17

Max Range: 1.4386. Min Range: -1.4386

Max Act: 0.9375. Min Act: -0.0001

Data Index: 1627698 (Python Code)

Max Activating Token Index: 462

Text #18

Max Range: 1.4386. Min Range: -1.4386

Max Act: 0.9703. Min Act: -0.0000

Data Index: 214609 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 1.4386. Min Range: -1.4386

Max Act: 0.9258. Min Act: -0.0001

Data Index: 651547 (C4 (Web Text))

Max Activating Token Index: 926