Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1861 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3521. Min Act: -0.0001

Data Index: 870695 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3213. Min Act: -0.0001

Data Index: 517127 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3144. Min Act: -0.0001

Data Index: 877489 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2635. Min Act: -0.0001

Data Index: 353708 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2914. Min Act: -0.0001

Data Index: 641158 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2830. Min Act: -0.0001

Data Index: 295434 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2544. Min Act: -0.0001

Data Index: 815327 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2386. Min Act: -0.0001

Data Index: 1358741 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2394. Min Act: -0.0001

Data Index: 606766 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2209. Min Act: -0.0001

Data Index: 36245 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2145. Min Act: -0.0001

Data Index: 900938 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2211. Min Act: -0.0001

Data Index: 556074 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.1935. Min Act: -0.0001

Data Index: 746583 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2061. Min Act: -0.0001

Data Index: 1309676 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2112. Min Act: -0.0001

Data Index: 276525 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.1930. Min Act: -0.0001

Data Index: 462545 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.1958. Min Act: -0.0001

Data Index: 830739 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.1874. Min Act: -0.0001

Data Index: 25015 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.1638. Min Act: -0.0001

Data Index: 135954 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.1739. Min Act: -0.0001

Data Index: 251289 (C4 (Web Text))

Max Activating Token Index: 921