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

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

Neuron 1182 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.9758. Min Act: -0.0000

Data Index: 61352 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.9279. Min Act: -0.0000

Data Index: 904560 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1421554 (Python Code)

Max Activating Token Index: 258

Text #3

Max Range: 1.2716. Min Range: -1.2716

Max Act: 1.2716. Min Act: -0.0001

Data Index: 627510 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.8660. Min Act: -0.0000

Data Index: 1482257 (Python Code)

Max Activating Token Index: 660

Text #5

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1452891 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.7260. Min Act: 0.0000

Data Index: 1403752 (Python Code)

Max Activating Token Index: 890

Text #7

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.6123. Min Act: -0.0000

Data Index: 541617 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.7521. Min Act: 0.0001

Data Index: 1622247 (Python Code)

Max Activating Token Index: 100

Text #9

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.7543. Min Act: -0.0000

Data Index: 689157 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.7030. Min Act: -0.0000

Data Index: 1452121 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1426943 (Python Code)

Max Activating Token Index: 865

Text #12

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.7419. Min Act: -0.0000

Data Index: 67456 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.5857. Min Act: -0.0001

Data Index: 1352226 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.7218. Min Act: -0.0001

Data Index: 1031062 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.5455. Min Act: -0.0000

Data Index: 592219 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.7013. Min Act: -0.0000

Data Index: 197924 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.6332. Min Act: -0.0000

Data Index: 763538 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.6706. Min Act: -0.0001

Data Index: 1525128 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.6916. Min Act: 0.0000

Data Index: 1390097 (Python Code)

Max Activating Token Index: 290