Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 326 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.8649. Min Act: -0.0000

Data Index: 54540 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.8513. Min Act: -0.0000

Data Index: 321106 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.8513. Min Act: -0.0000

Data Index: 589949 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.7914. Min Act: -0.0001

Data Index: 842245 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.6445. Min Act: -0.0000

Data Index: 214166 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.6396. Min Act: -0.0000

Data Index: 845978 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1268588 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.6500. Min Act: -0.0000

Data Index: 762851 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.6403. Min Act: -0.0000

Data Index: 275365 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.5907. Min Act: -0.0000

Data Index: 687217 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.5932. Min Act: -0.0000

Data Index: 29545 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.6312. Min Act: -0.0000

Data Index: 576667 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.6183. Min Act: -0.0001

Data Index: 198246 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.5800. Min Act: -0.0000

Data Index: 146158 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.5646. Min Act: -0.0000

Data Index: 913380 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.6116. Min Act: -0.0000

Data Index: 417808 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.5417. Min Act: -0.0001

Data Index: 287837 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1138490 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1038995 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.8649. Min Range: -0.8649

Max Act: 0.5148. Min Act: -0.0000

Data Index: 322774 (C4 (Web Text))

Max Activating Token Index: 532