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

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

Neuron 1252 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4821. Min Range: -1.4821

Max Act: 1.4821. Min Act: -0.0000

Data Index: 246707 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 1.4821. Min Range: -1.4821

Max Act: 1.3721. Min Act: -0.0000

Data Index: 1265436 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.4821. Min Range: -1.4821

Max Act: 1.3674. Min Act: -0.0000

Data Index: 497846 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 1.4821. Min Range: -1.4821

Max Act: 1.2651. Min Act: -0.0000

Data Index: 756314 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 1.4821. Min Range: -1.4821

Max Act: 1.1002. Min Act: -0.0000

Data Index: 640969 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 1.4821. Min Range: -1.4821

Max Act: 1.0363. Min Act: -0.0000

Data Index: 711556 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 1.4821. Min Range: -1.4821

Max Act: 1.0610. Min Act: -0.0000

Data Index: 814412 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 1.4821. Min Range: -1.4821

Max Act: 1.1621. Min Act: -0.0000

Data Index: 225010 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 1.4821. Min Range: -1.4821

Max Act: 1.0450. Min Act: -0.0000

Data Index: 1042164 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 1.4821. Min Range: -1.4821

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1102965 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 1.4821. Min Range: -1.4821

Max Act: 0.9567. Min Act: -0.0000

Data Index: 565995 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 1.4821. Min Range: -1.4821

Max Act: 0.9098. Min Act: -0.0000

Data Index: 665213 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 1.4821. Min Range: -1.4821

Max Act: 0.9412. Min Act: -0.0000

Data Index: 178624 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 1.4821. Min Range: -1.4821

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1211674 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 1.4821. Min Range: -1.4821

Max Act: 0.8528. Min Act: -0.0000

Data Index: 693648 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 1.4821. Min Range: -1.4821

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1159582 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 1.4821. Min Range: -1.4821

Max Act: 0.7475. Min Act: -0.0000

Data Index: 882512 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 1.4821. Min Range: -1.4821

Max Act: 0.7291. Min Act: -0.0000

Data Index: 880707 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 1.4821. Min Range: -1.4821

Max Act: 0.7213. Min Act: -0.0000

Data Index: 787091 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 1.4821. Min Range: -1.4821

Max Act: 0.6959. Min Act: -0.0000

Data Index: 983173 (C4 (Web Text))

Max Activating Token Index: 179