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

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

Neuron 3070 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: 0.5607. Min Range: -0.5607

Max Act: 0.5280. Min Act: -0.0002

Data Index: 862791 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.5291. Min Act: -0.0002

Data Index: 1006120 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.5607. Min Act: -0.0001

Data Index: 912980 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.5192. Min Act: -0.0001

Data Index: 1009129 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.5072. Min Act: -0.0001

Data Index: 963932 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4736. Min Act: -0.0001

Data Index: 45215 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.5174. Min Act: -0.0002

Data Index: 994084 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4793. Min Act: -0.0001

Data Index: 672100 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4980. Min Act: -0.0001

Data Index: 47964 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4463. Min Act: -0.0001

Data Index: 1335369 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4583. Min Act: -0.0001

Data Index: 566662 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3145. Min Act: -0.0002

Data Index: 673134 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3999. Min Act: -0.0001

Data Index: 513569 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4530. Min Act: -0.0001

Data Index: 853313 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4381. Min Act: -0.0002

Data Index: 262498 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4544. Min Act: -0.0001

Data Index: 45846 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4644. Min Act: -0.0002

Data Index: 694145 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4017. Min Act: -0.0002

Data Index: 910636 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4403. Min Act: -0.0002

Data Index: 677640 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4439. Min Act: -0.0001

Data Index: 3023 (C4 (Web Text))

Max Activating Token Index: 15