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

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

Neuron 2140 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1533765 (Python Code)

Max Activating Token Index: 944

Text #1

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2241. Min Act: -0.0001

Data Index: 980298 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2025. Min Act: 0.0000

Data Index: 707863 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2085. Min Act: -0.0000

Data Index: 345417 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2082. Min Act: -0.0000

Data Index: 691096 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2044. Min Act: -0.0001

Data Index: 375866 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1213428 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1466747 (Python Code)

Max Activating Token Index: 209

Text #8

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1531105 (Python Code)

Max Activating Token Index: 511

Text #9

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1799. Min Act: -0.0001

Data Index: 674291 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1872. Min Act: -0.0000

Data Index: 899068 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1007663 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1864. Min Act: -0.0000

Data Index: 56139 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1898. Min Act: -0.0001

Data Index: 908895 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1904. Min Act: -0.0000

Data Index: 707019 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1881. Min Act: -0.0001

Data Index: 1029061 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1387355 (Python Code)

Max Activating Token Index: 229

Text #17

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1864. Min Act: -0.0000

Data Index: 50462 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1305839 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1496075 (Python Code)

Max Activating Token Index: 300