Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4804 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1225. Min Act: -0.0002

Data Index: 1031495 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1197. Min Act: -0.0002

Data Index: 748513 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1149. Min Act: -0.0002

Data Index: 764637 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1005401 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1043. Min Act: -0.0002

Data Index: 211897 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1084. Min Act: -0.0002

Data Index: 271005 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1065. Min Act: -0.0002

Data Index: 700509 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1051. Min Act: -0.0002

Data Index: 515487 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1027. Min Act: -0.0002

Data Index: 1264603 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0972. Min Act: -0.0002

Data Index: 958297 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0934. Min Act: -0.0002

Data Index: 271255 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1166485 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0951. Min Act: -0.0002

Data Index: 189536 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1271167 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0954. Min Act: -0.0002

Data Index: 367215 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0934. Min Act: -0.0002

Data Index: 73277 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0964. Min Act: -0.0002

Data Index: 247732 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0933. Min Act: -0.0002

Data Index: 921090 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0878. Min Act: -0.0002

Data Index: 791107 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1263292 (C4 (Web Text))

Max Activating Token Index: 395