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

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

Neuron 2660 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: 1.7534. Min Range: -1.7534

Max Act: 1.7534. Min Act: -0.0003

Data Index: 731271 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.4313. Min Act: -0.0002

Data Index: 1143361 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.4284. Min Act: -0.0003

Data Index: 1103849 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.3803. Min Act: -0.0002

Data Index: 1359687 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.3380. Min Act: -0.0003

Data Index: 1230215 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.3083. Min Act: -0.0002

Data Index: 963452 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.3100. Min Act: -0.0003

Data Index: 1246723 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.3410. Min Act: -0.0003

Data Index: 840397 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.3263. Min Act: -0.0003

Data Index: 1157896 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.2753. Min Act: -0.0002

Data Index: 59202 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.2388. Min Act: -0.0003

Data Index: 78558 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.2764. Min Act: -0.0003

Data Index: 796022 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.2325. Min Act: -0.0003

Data Index: 1201796 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.2658. Min Act: -0.0003

Data Index: 701521 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.2734. Min Act: -0.0003

Data Index: 540143 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.1883. Min Act: -0.0002

Data Index: 703986 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.2130. Min Act: -0.0003

Data Index: 24376 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.2143. Min Act: -0.0002

Data Index: 116183 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.2750. Min Act: -0.0002

Data Index: 789158 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.2807. Min Act: -0.0003

Data Index: 536602 (C4 (Web Text))

Max Activating Token Index: 407