Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1085 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.4052. Min Act: -0.0002

Data Index: 97024 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.2829. Min Act: -0.0002

Data Index: 88751 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.1929. Min Act: -0.0001

Data Index: 46203 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.0740. Min Act: -0.0002

Data Index: 211289 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.0900. Min Act: -0.0002

Data Index: 1264454 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.2017. Min Act: -0.0001

Data Index: 1075667 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.2497. Min Act: -0.0002

Data Index: 362148 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.0655. Min Act: -0.0002

Data Index: 1243649 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.1532. Min Act: -0.0001

Data Index: 1052341 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.0730. Min Act: -0.0002

Data Index: 1213903 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.1411. Min Act: -0.0002

Data Index: 246266 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.0760. Min Act: -0.0001

Data Index: 1161751 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.1187. Min Act: -0.0002

Data Index: 1019784 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 1.4052. Min Range: -1.4052

Max Act: 0.9813. Min Act: -0.0002

Data Index: 658310 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.1230. Min Act: -0.0001

Data Index: 675264 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 1.4052. Min Range: -1.4052

Max Act: 0.8043. Min Act: -0.0002

Data Index: 1227306 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.0956. Min Act: -0.0002

Data Index: 237745 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 1.4052. Min Range: -1.4052

Max Act: 0.9812. Min Act: -0.0002

Data Index: 889639 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 1.4052. Min Range: -1.4052

Max Act: 1.0838. Min Act: -0.0001

Data Index: 968868 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 1.4052. Min Range: -1.4052

Max Act: 0.8933. Min Act: -0.0002

Data Index: 921284 (C4 (Web Text))

Max Activating Token Index: 322