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

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

Neuron 872 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1448963 (Python Code)

Max Activating Token Index: 168

Text #1

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1257111 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1000. Min Act: -0.0001

Data Index: 245623 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1029. Min Act: -0.0001

Data Index: 726382 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1518675 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0968. Min Act: -0.0001

Data Index: 941718 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0948. Min Act: -0.0001

Data Index: 372355 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1008. Min Act: -0.0001

Data Index: 726282 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0898. Min Act: -0.0001

Data Index: 225529 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0901. Min Act: -0.0001

Data Index: 399016 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0934. Min Act: -0.0001

Data Index: 929124 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1577607 (Python Code)

Max Activating Token Index: 942

Text #12

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0925. Min Act: -0.0001

Data Index: 820662 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1455378 (Python Code)

Max Activating Token Index: 335

Text #14

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0871. Min Act: -0.0001

Data Index: 623566 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0845. Min Act: -0.0001

Data Index: 616377 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0870. Min Act: -0.0001

Data Index: 672020 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1179181 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0886. Min Act: -0.0001

Data Index: 723605 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1425997 (Python Code)

Max Activating Token Index: 1022