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

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

Neuron 2561 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: 0.1153. Min Range: -0.1153

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1331689 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0900. Min Act: -0.0002

Data Index: 394233 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0907. Min Act: -0.0001

Data Index: 183118 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1275999 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0814. Min Act: -0.0002

Data Index: 140722 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1302515 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0801. Min Act: -0.0002

Data Index: 725515 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0804. Min Act: -0.0002

Data Index: 632871 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0794. Min Act: -0.0002

Data Index: 38586 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0807. Min Act: -0.0002

Data Index: 201271 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0750. Min Act: -0.0002

Data Index: 46291 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0841. Min Act: -0.0002

Data Index: 227012 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0686. Min Act: -0.0002

Data Index: 565381 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0686. Min Act: -0.0002

Data Index: 925304 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1168333 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0746. Min Act: -0.0002

Data Index: 934715 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1335529 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0808. Min Act: -0.0001

Data Index: 261809 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0764. Min Act: -0.0002

Data Index: 198292 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1261286 (C4 (Web Text))

Max Activating Token Index: 246