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

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

Neuron 1251 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: 1.3088. Min Range: -1.3088

Max Act: 1.3088. Min Act: -0.0002

Data Index: 1203357 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.1682. Min Act: -0.0002

Data Index: 473329 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.2476. Min Act: -0.0001

Data Index: 30664 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0187. Min Act: -0.0002

Data Index: 628697 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0999. Min Act: -0.0002

Data Index: 129057 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0491. Min Act: -0.0002

Data Index: 593751 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.1684. Min Act: -0.0002

Data Index: 1355166 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.1435. Min Act: -0.0002

Data Index: 349418 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.1406. Min Act: -0.0001

Data Index: 217082 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.1025. Min Act: -0.0001

Data Index: 364315 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0642. Min Act: -0.0002

Data Index: 634826 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9722. Min Act: -0.0001

Data Index: 1201178 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0241. Min Act: -0.0002

Data Index: 796496 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.1015. Min Act: -0.0001

Data Index: 772147 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0612. Min Act: -0.0001

Data Index: 27964 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0683. Min Act: -0.0002

Data Index: 130239 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.8112. Min Act: -0.0001

Data Index: 270317 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0254. Min Act: -0.0001

Data Index: 778360 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0176. Min Act: -0.0002

Data Index: 1175396 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9494. Min Act: -0.0002

Data Index: 1294398 (C4 (Web Text))

Max Activating Token Index: 794