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

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

Neuron 5108 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.1112. Min Act: -0.0002

Data Index: 1242582 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.0663. Min Act: -0.0002

Data Index: 369720 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.0039. Min Act: -0.0002

Data Index: 393312 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.0121. Min Act: -0.0002

Data Index: 1158907 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9970. Min Act: -0.0002

Data Index: 227333 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 1.1112. Min Range: -1.1112

Max Act: 1.0069. Min Act: -0.0002

Data Index: 945047 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9650. Min Act: -0.0002

Data Index: 613936 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9687. Min Act: -0.0002

Data Index: 80682 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9784. Min Act: -0.0002

Data Index: 1063817 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9830. Min Act: -0.0002

Data Index: 587274 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9836. Min Act: -0.0003

Data Index: 300350 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9853. Min Act: -0.0002

Data Index: 1327514 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9762. Min Act: -0.0002

Data Index: 222095 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9451. Min Act: -0.0002

Data Index: 991978 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9528. Min Act: -0.0002

Data Index: 771472 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9588. Min Act: -0.0003

Data Index: 1002187 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9441. Min Act: -0.0002

Data Index: 962750 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9430. Min Act: -0.0002

Data Index: 340267 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9521. Min Act: -0.0002

Data Index: 888670 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 1.1112. Min Range: -1.1112

Max Act: 0.9474. Min Act: -0.0002

Data Index: 1094688 (C4 (Web Text))

Max Activating Token Index: 64