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

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

Neuron 5089 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.1281. Min Act: -0.0002

Data Index: 698479 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9701. Min Act: -0.0002

Data Index: 921068 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.1657. Min Act: -0.0002

Data Index: 240756 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.2056. Min Act: -0.0002

Data Index: 1165843 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9273. Min Act: -0.0002

Data Index: 971924 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0429. Min Act: -0.0002

Data Index: 900991 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0679. Min Act: -0.0002

Data Index: 483538 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0707. Min Act: -0.0002

Data Index: 782187 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0645. Min Act: -0.0002

Data Index: 732578 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9371. Min Act: -0.0002

Data Index: 42854 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0562. Min Act: -0.0002

Data Index: 1182914 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9018. Min Act: -0.0002

Data Index: 1067607 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.2263. Min Act: -0.0002

Data Index: 1283286 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0850. Min Act: -0.0002

Data Index: 320513 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0106. Min Act: -0.0002

Data Index: 368101 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.1035. Min Act: -0.0002

Data Index: 57847 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9455. Min Act: -0.0002

Data Index: 1037423 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9716. Min Act: -0.0002

Data Index: 1175240 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9989. Min Act: -0.0002

Data Index: 1187519 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0073. Min Act: -0.0002

Data Index: 40229 (C4 (Web Text))

Max Activating Token Index: 70