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

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

Neuron 2581 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3552. Min Act: -0.0001

Data Index: 173220 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3442. Min Act: -0.0001

Data Index: 404207 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3474. Min Act: -0.0001

Data Index: 1641856 (Python Code)

Max Activating Token Index: 816

Text #3

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1623608 (Python Code)

Max Activating Token Index: 815

Text #4

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1547574 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3231. Min Act: -0.0000

Data Index: 1598449 (Python Code)

Max Activating Token Index: 873

Text #6

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3210. Min Act: -0.0001

Data Index: 1636296 (Python Code)

Max Activating Token Index: 238

Text #7

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1549637 (Python Code)

Max Activating Token Index: 1003

Text #8

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2983. Min Act: -0.0001

Data Index: 646798 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2928. Min Act: -0.0001

Data Index: 1377178 (Python Code)

Max Activating Token Index: 573

Text #10

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2864. Min Act: 0.0000

Data Index: 1596521 (Python Code)

Max Activating Token Index: 686

Text #11

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2941. Min Act: -0.0001

Data Index: 536064 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2955. Min Act: -0.0001

Data Index: 1521409 (Python Code)

Max Activating Token Index: 818

Text #13

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1539885 (Python Code)

Max Activating Token Index: 877

Text #14

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2745. Min Act: 0.0000

Data Index: 1596779 (Python Code)

Max Activating Token Index: 153

Text #15

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2729. Min Act: -0.0000

Data Index: 46748 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2794. Min Act: -0.0001

Data Index: 634816 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1550930 (Python Code)

Max Activating Token Index: 541

Text #18

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1412731 (Python Code)

Max Activating Token Index: 788

Text #19

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1421116 (Python Code)

Max Activating Token Index: 714