Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2805 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1872. Min Range: -2.1872

Max Act: 2.1872. Min Act: -0.0000

Data Index: 967140 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.6270. Min Act: -0.0000

Data Index: 373006 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.5013. Min Act: -0.0000

Data Index: 603325 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.4174. Min Act: -0.0000

Data Index: 1058707 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.4809. Min Act: -0.0000

Data Index: 582609 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.3255. Min Act: -0.0000

Data Index: 1248670 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.3779. Min Act: -0.0000

Data Index: 1325863 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.3626. Min Act: -0.0000

Data Index: 1048461 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.2521. Min Act: -0.0000

Data Index: 1288738 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.3237. Min Act: -0.0000

Data Index: 240577 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.1523. Min Act: -0.0000

Data Index: 529061 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.3056. Min Act: -0.0000

Data Index: 1010257 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 2.1872. Min Range: -2.1872

Max Act: 0.9825. Min Act: -0.0000

Data Index: 20610 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.2118. Min Act: -0.0000

Data Index: 756135 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.2833. Min Act: -0.0000

Data Index: 699740 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.1844. Min Act: -0.0000

Data Index: 935640 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1537307 (Python Code)

Max Activating Token Index: 364

Text #17

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.1041. Min Act: -0.0000

Data Index: 116242 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.2365. Min Act: -0.0000

Data Index: 349382 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.1511. Min Act: -0.0000

Data Index: 826108 (C4 (Web Text))

Max Activating Token Index: 201