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

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

Neuron 853 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.1562. Min Act: -0.0000

Data Index: 462347 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.0712. Min Act: -0.0000

Data Index: 152834 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.1416. Min Act: -0.0000

Data Index: 146124 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1319057 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.0432. Min Act: -0.0000

Data Index: 289398 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.0345. Min Act: -0.0000

Data Index: 280352 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.0885. Min Act: -0.0000

Data Index: 1199693 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9846. Min Act: -0.0000

Data Index: 311692 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9955. Min Act: -0.0000

Data Index: 786816 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.8942. Min Act: -0.0000

Data Index: 969969 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1073182 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.0066. Min Act: -0.0000

Data Index: 975643 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1295865 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1274859 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9014. Min Act: -0.0000

Data Index: 283828 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9380. Min Act: -0.0000

Data Index: 271462 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1154541 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1120855 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.8919. Min Act: -0.0000

Data Index: 37753 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.8851. Min Act: -0.0000

Data Index: 1353828 (C4 (Web Text))

Max Activating Token Index: 922