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

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

Neuron 3678 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0946. Min Act: -0.0003

Data Index: 60223 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.1004. Min Act: -0.0003

Data Index: 222498 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0846. Min Act: -0.0003

Data Index: 793591 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0861. Min Act: -0.0003

Data Index: 342305 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0997. Min Act: -0.0003

Data Index: 364133 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1077022 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0885. Min Act: -0.0003

Data Index: 63194 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0874. Min Act: -0.0003

Data Index: 1030545 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0882. Min Act: -0.0003

Data Index: 905214 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0855. Min Act: -0.0003

Data Index: 966388 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0867. Min Act: -0.0003

Data Index: 1168854 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0788. Min Act: -0.0003

Data Index: 688840 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0851. Min Act: -0.0002

Data Index: 967534 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0736. Min Act: -0.0003

Data Index: 260820 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0789. Min Act: -0.0002

Data Index: 51461 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0862. Min Act: -0.0003

Data Index: 916358 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0713. Min Act: -0.0003

Data Index: 996794 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0839. Min Act: -0.0003

Data Index: 256660 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0763. Min Act: -0.0003

Data Index: 421579 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0821. Min Act: -0.0003

Data Index: 786048 (C4 (Web Text))

Max Activating Token Index: 521