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

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

Neuron 2705 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: 0.2469. Min Range: -0.2469

Max Act: 0.2444. Min Act: -0.0003

Data Index: 620819 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2417. Min Act: -0.0003

Data Index: 991492 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2469. Min Act: -0.0003

Data Index: 4887 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2357. Min Act: -0.0002

Data Index: 625334 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2344. Min Act: -0.0002

Data Index: 1010609 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2249. Min Act: -0.0002

Data Index: 685138 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2158. Min Act: -0.0002

Data Index: 289820 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2181. Min Act: -0.0003

Data Index: 183895 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2095. Min Act: -0.0003

Data Index: 886007 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2061. Min Act: -0.0002

Data Index: 198726 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2115. Min Act: -0.0002

Data Index: 969449 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2126. Min Act: -0.0002

Data Index: 2609 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2101. Min Act: -0.0003

Data Index: 940096 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2097. Min Act: -0.0002

Data Index: 234120 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1911. Min Act: -0.0003

Data Index: 616104 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1851. Min Act: -0.0003

Data Index: 1311526 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2023. Min Act: -0.0002

Data Index: 275017 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2016. Min Act: -0.0002

Data Index: 978066 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1946. Min Act: -0.0002

Data Index: 450296 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2068. Min Act: -0.0002

Data Index: 452374 (C4 (Web Text))

Max Activating Token Index: 616