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

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

Neuron 3968 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3809. Min Act: -0.0003

Data Index: 1358901 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3741. Min Act: -0.0003

Data Index: 1319325 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3960. Min Act: -0.0003

Data Index: 1114151 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3554. Min Act: -0.0003

Data Index: 143628 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3040. Min Act: -0.0003

Data Index: 174272 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3007. Min Act: -0.0002

Data Index: 655614 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2911. Min Act: -0.0003

Data Index: 695478 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2911. Min Act: -0.0002

Data Index: 368970 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2839. Min Act: -0.0003

Data Index: 972220 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2819. Min Act: -0.0003

Data Index: 280854 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2794. Min Act: -0.0003

Data Index: 46136 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2784. Min Act: -0.0003

Data Index: 600564 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2756. Min Act: -0.0003

Data Index: 371527 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2627. Min Act: -0.0003

Data Index: 501219 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2606. Min Act: -0.0002

Data Index: 1059916 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2505. Min Act: -0.0003

Data Index: 131891 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2493. Min Act: -0.0003

Data Index: 745302 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2620. Min Act: -0.0003

Data Index: 1241299 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2351. Min Act: -0.0003

Data Index: 235009 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2350. Min Act: -0.0003

Data Index: 625628 (C4 (Web Text))

Max Activating Token Index: 486