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

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

Neuron 1660 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7237. Min Act: -0.0001

Data Index: 443627 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.6545. Min Act: -0.0001

Data Index: 1635027 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.6917. Min Act: -0.0001

Data Index: 1219056 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7719. Min Act: -0.0001

Data Index: 169942 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.6757. Min Act: -0.0001

Data Index: 1113073 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.6436. Min Act: -0.0001

Data Index: 920842 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.5721. Min Act: -0.0000

Data Index: 587788 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.5065. Min Act: -0.0001

Data Index: 1521039 (Python Code)

Max Activating Token Index: 21

Text #8

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.4751. Min Act: -0.0001

Data Index: 1580658 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.5092. Min Act: -0.0001

Data Index: 1445953 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.4936. Min Act: -0.0001

Data Index: 1648885 (Python Code)

Max Activating Token Index: 671

Text #11

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.4641. Min Act: -0.0000

Data Index: 318767 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.5330. Min Act: -0.0000

Data Index: 1404460 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.4592. Min Act: -0.0001

Data Index: 520928 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.5085. Min Act: -0.0001

Data Index: 1530212 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.3126. Min Act: -0.0001

Data Index: 346747 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.4293. Min Act: -0.0001

Data Index: 1097910 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.6570. Min Act: -0.0001

Data Index: 396105 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.4220. Min Act: -0.0001

Data Index: 1494749 (Python Code)

Max Activating Token Index: 947

Text #19

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.3725. Min Act: -0.0000

Data Index: 712483 (C4 (Web Text))

Max Activating Token Index: 307