Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 157 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0897. Min Act: -0.0003

Data Index: 196652 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0927. Min Act: -0.0003

Data Index: 515542 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0848. Min Act: -0.0003

Data Index: 1102167 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0844. Min Act: -0.0003

Data Index: 697746 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0808. Min Act: -0.0003

Data Index: 1225742 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0802. Min Act: -0.0003

Data Index: 25914 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0760. Min Act: -0.0003

Data Index: 337125 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0757. Min Act: -0.0003

Data Index: 309513 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1202672 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1180708 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0701. Min Act: -0.0003

Data Index: 540363 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0730. Min Act: -0.0003

Data Index: 319806 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0709. Min Act: -0.0003

Data Index: 255440 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0695. Min Act: -0.0003

Data Index: 741696 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0722. Min Act: -0.0003

Data Index: 127382 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0689. Min Act: -0.0003

Data Index: 730996 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1211510 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0734. Min Act: -0.0003

Data Index: 321092 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0729. Min Act: -0.0003

Data Index: 528617 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0683. Min Act: -0.0003

Data Index: 273081 (C4 (Web Text))

Max Activating Token Index: 137