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

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

Neuron 1302 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: 1.0516. Min Range: -1.0516

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1419586 (Python Code)

Max Activating Token Index: 625

Text #1

Max Range: 1.0516. Min Range: -1.0516

Max Act: 1.0516. Min Act: -0.0000

Data Index: 1560611 (Python Code)

Max Activating Token Index: 161

Text #2

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1646017 (Python Code)

Max Activating Token Index: 39

Text #3

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1644982 (Python Code)

Max Activating Token Index: 225

Text #4

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1656695 (Python Code)

Max Activating Token Index: 735

Text #5

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1410620 (Python Code)

Max Activating Token Index: 896

Text #6

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1341206 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1615764 (Python Code)

Max Activating Token Index: 663

Text #8

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1537581 (Python Code)

Max Activating Token Index: 1003

Text #9

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1508090 (Python Code)

Max Activating Token Index: 212

Text #10

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1374430 (Python Code)

Max Activating Token Index: 431

Text #11

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1583861 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6689. Min Act: -0.0000

Data Index: 780287 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1372893 (Python Code)

Max Activating Token Index: 246

Text #14

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1644047 (Python Code)

Max Activating Token Index: 126

Text #15

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1311412 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1424322 (Python Code)

Max Activating Token Index: 382

Text #17

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6008. Min Act: 0.0000

Data Index: 375738 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1020123 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.5588. Min Act: -0.0000

Data Index: 964557 (C4 (Web Text))

Max Activating Token Index: 20