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

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

Neuron 4507 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1332. Min Act: -0.0002

Data Index: 547254 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1099. Min Act: -0.0002

Data Index: 280385 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0986. Min Act: -0.0002

Data Index: 44618 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0985. Min Act: -0.0002

Data Index: 112817 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1103789 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1057. Min Act: -0.0002

Data Index: 1244989 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0982. Min Act: -0.0002

Data Index: 59827 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0922. Min Act: -0.0002

Data Index: 752354 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1301164 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1226693 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0916. Min Act: -0.0002

Data Index: 663731 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0923. Min Act: -0.0002

Data Index: 585725 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1055620 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0876. Min Act: -0.0002

Data Index: 421420 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1283892 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0845. Min Act: -0.0002

Data Index: 486438 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0899. Min Act: -0.0002

Data Index: 891160 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0918. Min Act: -0.0002

Data Index: 986036 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0948. Min Act: -0.0002

Data Index: 831717 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0883. Min Act: -0.0002

Data Index: 622387 (C4 (Web Text))

Max Activating Token Index: 342