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

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

Neuron 2588 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3136. Min Range: -2.3136

Max Act: 2.3136. Min Act: -0.0000

Data Index: 1115678 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 2.3136. Min Range: -2.3136

Max Act: 2.2563. Min Act: -0.0000

Data Index: 1388649 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.9570. Min Act: -0.0000

Data Index: 1164367 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.9067. Min Act: -0.0000

Data Index: 559397 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.6916. Min Act: -0.0000

Data Index: 843044 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.6849. Min Act: -0.0000

Data Index: 1523113 (Python Code)

Max Activating Token Index: 924

Text #6

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.6808. Min Act: -0.0000

Data Index: 1626269 (Python Code)

Max Activating Token Index: 311

Text #7

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.6401. Min Act: -0.0000

Data Index: 1505002 (Python Code)

Max Activating Token Index: 775

Text #8

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.6405. Min Act: -0.0000

Data Index: 414892 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1609479 (Python Code)

Max Activating Token Index: 659

Text #10

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.6403. Min Act: -0.0000

Data Index: 681967 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.6228. Min Act: -0.0000

Data Index: 1223468 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.5104. Min Act: -0.0000

Data Index: 797144 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.6840. Min Act: -0.0000

Data Index: 1067359 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.5978. Min Act: -0.0000

Data Index: 1214643 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.5480. Min Act: -0.0000

Data Index: 1454729 (Python Code)

Max Activating Token Index: 373

Text #16

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.5900. Min Act: -0.0000

Data Index: 182126 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.5578. Min Act: -0.0000

Data Index: 274078 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.5240. Min Act: -0.0000

Data Index: 679229 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 2.3136. Min Range: -2.3136

Max Act: 1.5188. Min Act: -0.0000

Data Index: 1401799 (Python Code)

Max Activating Token Index: 901