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

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

Neuron 2931 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1192. Min Act: -0.0002

Data Index: 998240 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0994. Min Act: -0.0002

Data Index: 751121 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0995. Min Act: -0.0002

Data Index: 129084 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1251336 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0935. Min Act: -0.0002

Data Index: 237121 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0922. Min Act: -0.0002

Data Index: 177924 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0843. Min Act: -0.0002

Data Index: 367629 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0842. Min Act: -0.0002

Data Index: 335333 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0844. Min Act: -0.0002

Data Index: 949955 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1185193 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0854. Min Act: -0.0002

Data Index: 161240 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0808. Min Act: -0.0002

Data Index: 868163 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0819. Min Act: -0.0002

Data Index: 592767 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0771. Min Act: -0.0002

Data Index: 305175 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1289113 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1058693 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0785. Min Act: -0.0002

Data Index: 660559 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0742. Min Act: -0.0002

Data Index: 371050 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1282534 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0757. Min Act: -0.0002

Data Index: 885948 (C4 (Web Text))

Max Activating Token Index: 614