Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2337 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.8265. Min Act: -0.0000

Data Index: 337029 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.7474. Min Act: -0.0000

Data Index: 987899 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1312120 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1089771 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6368. Min Act: -0.0000

Data Index: 453876 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6251. Min Act: -0.0000

Data Index: 729311 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5900. Min Act: -0.0000

Data Index: 6260 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5446. Min Act: -0.0000

Data Index: 964696 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1177718 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1066676 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5212. Min Act: -0.0000

Data Index: 821112 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5327. Min Act: -0.0000

Data Index: 343953 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5109. Min Act: -0.0000

Data Index: 441607 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1110645 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5097. Min Act: -0.0000

Data Index: 882906 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1108047 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.4881. Min Act: -0.0000

Data Index: 487765 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.4892. Min Act: -0.0000

Data Index: 287736 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5020. Min Act: -0.0000

Data Index: 868062 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.4801. Min Act: -0.0000

Data Index: 267062 (C4 (Web Text))

Max Activating Token Index: 969