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

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

Neuron 2791 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: 0.8444. Min Range: -0.8444

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1219098 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.8036. Min Act: -0.0000

Data Index: 557028 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7697. Min Act: -0.0000

Data Index: 720293 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1027243 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7487. Min Act: -0.0000

Data Index: 955513 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7337. Min Act: -0.0001

Data Index: 702329 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7062. Min Act: -0.0001

Data Index: 1063680 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.6763. Min Act: -0.0001

Data Index: 75776 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7381. Min Act: -0.0000

Data Index: 253821 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.7124. Min Act: -0.0000

Data Index: 266934 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1004969 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.6680. Min Act: -0.0000

Data Index: 470732 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.6751. Min Act: -0.0001

Data Index: 726588 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.6957. Min Act: -0.0001

Data Index: 113984 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1196431 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.6616. Min Act: -0.0001

Data Index: 689313 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.6185. Min Act: -0.0000

Data Index: 70401 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.6465. Min Act: -0.0000

Data Index: 1296217 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.6421. Min Act: -0.0001

Data Index: 1205087 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.8444. Min Range: -0.8444

Max Act: 0.6220. Min Act: -0.0000

Data Index: 519724 (C4 (Web Text))

Max Activating Token Index: 73