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

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

Neuron 8 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.3083. Min Act: -0.0003

Data Index: 958514 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.3138. Min Act: -0.0002

Data Index: 267324 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.3128. Min Act: -0.0003

Data Index: 763432 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.3074. Min Act: -0.0003

Data Index: 1154955 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.3023. Min Act: -0.0002

Data Index: 118085 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.3114. Min Act: -0.0003

Data Index: 1322013 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2976. Min Act: -0.0003

Data Index: 138218 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.3076. Min Act: -0.0003

Data Index: 1257473 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2945. Min Act: -0.0003

Data Index: 419792 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2914. Min Act: -0.0003

Data Index: 760466 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2719. Min Act: -0.0003

Data Index: 1218903 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2897. Min Act: -0.0003

Data Index: 411612 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2847. Min Act: -0.0002

Data Index: 391249 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2829. Min Act: -0.0003

Data Index: 861463 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2817. Min Act: -0.0002

Data Index: 826725 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2814. Min Act: -0.0003

Data Index: 164056 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2765. Min Act: -0.0003

Data Index: 442205 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2834. Min Act: -0.0003

Data Index: 549156 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2735. Min Act: -0.0003

Data Index: 518956 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2634. Min Act: -0.0003

Data Index: 833004 (C4 (Web Text))

Max Activating Token Index: 649