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

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

Neuron 5721 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5924. Min Act: -0.0000

Data Index: 528984 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1135888 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4697. Min Act: -0.0000

Data Index: 978946 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1158143 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1179564 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4454. Min Act: -0.0000

Data Index: 39771 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4535. Min Act: -0.0000

Data Index: 821386 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1310174 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4482. Min Act: -0.0000

Data Index: 815012 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4342. Min Act: -0.0000

Data Index: 835342 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4436. Min Act: -0.0000

Data Index: 923710 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1100161 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1223598 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1132018 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4335. Min Act: -0.0000

Data Index: 977161 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4314. Min Act: -0.0000

Data Index: 526133 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1297810 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4218. Min Act: -0.0000

Data Index: 946030 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1011533 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1333565 (C4 (Web Text))

Max Activating Token Index: 440