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

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

Neuron 4021 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.1107. Min Act: -0.0001

Data Index: 667814 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0954. Min Act: -0.0001

Data Index: 191772 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1022521 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0825. Min Act: -0.0001

Data Index: 197489 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0870. Min Act: -0.0001

Data Index: 35765 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0799. Min Act: -0.0001

Data Index: 967266 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0818. Min Act: -0.0001

Data Index: 356120 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0840. Min Act: -0.0001

Data Index: 265838 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0763. Min Act: -0.0001

Data Index: 589794 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0763. Min Act: -0.0001

Data Index: 709826 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0738. Min Act: -0.0001

Data Index: 1318145 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0751. Min Act: -0.0001

Data Index: 922727 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1160283 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0742. Min Act: -0.0001

Data Index: 136177 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0819. Min Act: -0.0001

Data Index: 740954 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0790. Min Act: -0.0001

Data Index: 49868 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0753. Min Act: -0.0001

Data Index: 910749 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0713. Min Act: -0.0001

Data Index: 906413 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0727. Min Act: -0.0001

Data Index: 1351948 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1357169 (C4 (Web Text))

Max Activating Token Index: 404