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

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

Neuron 3189 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1827. Min Range: -2.1827

Max Act: 2.1827. Min Act: -0.0000

Data Index: 83167 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 2.1827. Min Range: -2.1827

Max Act: 2.0340. Min Act: -0.0000

Data Index: 1343624 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.9064. Min Act: -0.0000

Data Index: 833250 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 2.1827. Min Range: -2.1827

Max Act: 2.0130. Min Act: -0.0000

Data Index: 196094 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.9994. Min Act: -0.0000

Data Index: 1108709 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.8726. Min Act: -0.0000

Data Index: 1275544 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.8603. Min Act: -0.0000

Data Index: 965299 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.8496. Min Act: -0.0000

Data Index: 1309180 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 2.1827. Min Range: -2.1827

Max Act: 2.1600. Min Act: -0.0000

Data Index: 783856 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.8311. Min Act: -0.0000

Data Index: 1208729 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.8297. Min Act: -0.0000

Data Index: 893302 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.9375. Min Act: -0.0000

Data Index: 834534 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 2.1827. Min Range: -2.1827

Max Act: 2.0154. Min Act: -0.0000

Data Index: 1320927 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.7766. Min Act: -0.0000

Data Index: 1262876 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.9320. Min Act: -0.0000

Data Index: 1017321 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.9120. Min Act: -0.0000

Data Index: 592595 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.8983. Min Act: -0.0000

Data Index: 595069 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.8989. Min Act: -0.0000

Data Index: 837156 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.8839. Min Act: -0.0000

Data Index: 405001 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 2.1827. Min Range: -2.1827

Max Act: 1.8863. Min Act: -0.0000

Data Index: 1083008 (C4 (Web Text))

Max Activating Token Index: 380