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

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

Neuron 3250 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: 0.2933. Min Range: -0.2933

Max Act: 0.2933. Min Act: -0.0000

Data Index: 900482 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2655. Min Act: -0.0000

Data Index: 714479 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2298. Min Act: -0.0000

Data Index: 966127 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1180740 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2252. Min Act: -0.0000

Data Index: 967322 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2164. Min Act: -0.0000

Data Index: 815917 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1990. Min Act: -0.0000

Data Index: 74879 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2107. Min Act: -0.0000

Data Index: 291300 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1972. Min Act: -0.0000

Data Index: 585543 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1991. Min Act: -0.0000

Data Index: 383173 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1984. Min Act: -0.0000

Data Index: 521105 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1980. Min Act: -0.0000

Data Index: 587130 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1979. Min Act: -0.0000

Data Index: 568914 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1016265 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1915. Min Act: -0.0000

Data Index: 920333 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1973. Min Act: -0.0000

Data Index: 873541 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1877. Min Act: -0.0000

Data Index: 19322 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1837. Min Act: -0.0000

Data Index: 352682 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1911. Min Act: -0.0000

Data Index: 125681 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1897. Min Act: -0.0000

Data Index: 251643 (C4 (Web Text))

Max Activating Token Index: 694