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

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

Neuron 772 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.3011. Min Act: -0.0001

Data Index: 1581173 (Python Code)

Max Activating Token Index: 699

Text #1

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1381442 (Python Code)

Max Activating Token Index: 977

Text #2

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2758. Min Act: -0.0000

Data Index: 18639 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2564. Min Act: -0.0000

Data Index: 760512 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1296783 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1574582 (Python Code)

Max Activating Token Index: 773

Text #6

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1615380 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1655500 (Python Code)

Max Activating Token Index: 352

Text #8

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2209. Min Act: -0.0000

Data Index: 972573 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2178. Min Act: -0.0000

Data Index: 502102 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1125057 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1983. Min Act: -0.0000

Data Index: 188808 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1972. Min Act: -0.0000

Data Index: 898615 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2033. Min Act: -0.0000

Data Index: 82433 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1563084 (Python Code)

Max Activating Token Index: 676

Text #15

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1569850 (Python Code)

Max Activating Token Index: 275

Text #16

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1964. Min Act: -0.0000

Data Index: 461503 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1627771 (Python Code)

Max Activating Token Index: 114

Text #18

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1931. Min Act: -0.0000

Data Index: 410793 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1924. Min Act: -0.0000

Data Index: 727469 (C4 (Web Text))

Max Activating Token Index: 53