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

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

Neuron 182 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: 0.7688. Min Range: -0.7688

Max Act: 0.7688. Min Act: -0.0001

Data Index: 365828 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7590. Min Act: -0.0002

Data Index: 597797 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6438. Min Act: -0.0002

Data Index: 1078650 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6743. Min Act: -0.0002

Data Index: 247536 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6295. Min Act: -0.0001

Data Index: 1045269 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6201. Min Act: -0.0002

Data Index: 369239 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6146. Min Act: -0.0002

Data Index: 1018656 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6401. Min Act: -0.0002

Data Index: 1022183 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6022. Min Act: -0.0002

Data Index: 28238 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5856. Min Act: -0.0002

Data Index: 894900 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5653. Min Act: -0.0002

Data Index: 1262024 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5465. Min Act: -0.0002

Data Index: 483890 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5328. Min Act: -0.0001

Data Index: 1319680 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5863. Min Act: -0.0002

Data Index: 1123838 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5758. Min Act: -0.0002

Data Index: 934916 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5747. Min Act: -0.0001

Data Index: 739827 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5582. Min Act: -0.0002

Data Index: 1130672 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5212. Min Act: -0.0002

Data Index: 525910 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5704. Min Act: -0.0002

Data Index: 142446 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5160. Min Act: -0.0002

Data Index: 323690 (C4 (Web Text))

Max Activating Token Index: 964