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

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

Neuron 3719 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2569. Min Act: -0.0000

Data Index: 62084 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2650. Min Act: -0.0000

Data Index: 277332 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2422. Min Act: -0.0000

Data Index: 117645 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2349. Min Act: -0.0000

Data Index: 670826 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1096573 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1267299 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2300. Min Act: -0.0000

Data Index: 737017 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2196. Min Act: -0.0000

Data Index: 945729 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1989. Min Act: -0.0000

Data Index: 113990 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2038. Min Act: -0.0000

Data Index: 440056 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2029. Min Act: -0.0000

Data Index: 114393 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1136237 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2001. Min Act: -0.0000

Data Index: 837235 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1052787 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1138883 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2003. Min Act: -0.0000

Data Index: 798958 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2083. Min Act: -0.0000

Data Index: 723553 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1072887 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1739. Min Act: -0.0000

Data Index: 884369 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1907. Min Act: -0.0000

Data Index: 27134 (C4 (Web Text))

Max Activating Token Index: 343