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

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

Neuron 734 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1273427 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.3234. Min Act: -0.0000

Data Index: 641535 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.3124. Min Act: -0.0000

Data Index: 79298 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.3115. Min Act: -0.0000

Data Index: 512311 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.3110. Min Act: -0.0000

Data Index: 610437 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1143836 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.3215. Min Act: -0.0000

Data Index: 300401 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1054236 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2944. Min Act: -0.0000

Data Index: 598186 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2861. Min Act: -0.0000

Data Index: 1203720 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1038006 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2773. Min Act: -0.0000

Data Index: 892975 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1274821 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2815. Min Act: -0.0000

Data Index: 52691 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2759. Min Act: -0.0000

Data Index: 302984 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2650. Min Act: -0.0000

Data Index: 211301 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1250768 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2560. Min Act: -0.0000

Data Index: 352144 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2606. Min Act: -0.0000

Data Index: 918712 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1314273 (C4 (Web Text))

Max Activating Token Index: 552