Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 783 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0921. Min Act: -0.0003

Data Index: 106285 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0918. Min Act: -0.0003

Data Index: 476610 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0846. Min Act: -0.0003

Data Index: 1287276 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0906. Min Act: -0.0003

Data Index: 206621 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0944. Min Act: -0.0003

Data Index: 88427 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0881. Min Act: -0.0003

Data Index: 178430 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0897. Min Act: -0.0003

Data Index: 499774 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0858. Min Act: -0.0003

Data Index: 293740 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0884. Min Act: -0.0003

Data Index: 1099135 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0894. Min Act: -0.0003

Data Index: 1338181 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0824. Min Act: -0.0003

Data Index: 1260903 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0760. Min Act: -0.0003

Data Index: 605056 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1446249 (Python Code)

Max Activating Token Index: 599

Text #13

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0879. Min Act: -0.0003

Data Index: 676692 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0847. Min Act: -0.0003

Data Index: 947335 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0949. Min Act: -0.0003

Data Index: 143528 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0835. Min Act: -0.0003

Data Index: 1212734 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0861. Min Act: -0.0003

Data Index: 1298620 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0858. Min Act: -0.0003

Data Index: 1059802 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0799. Min Act: -0.0003

Data Index: 1088103 (C4 (Web Text))

Max Activating Token Index: 510