Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3048 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3861. Min Act: -0.0001

Data Index: 107178 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.2885. Min Act: -0.0001

Data Index: 1174134 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3511. Min Act: -0.0001

Data Index: 839800 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.2894. Min Act: -0.0001

Data Index: 560906 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3012. Min Act: -0.0001

Data Index: 19291 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3685. Min Act: -0.0001

Data Index: 304861 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3519. Min Act: -0.0001

Data Index: 1073579 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.2753. Min Act: -0.0001

Data Index: 466085 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3243. Min Act: -0.0001

Data Index: 1122985 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3100. Min Act: -0.0001

Data Index: 223017 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3194. Min Act: -0.0001

Data Index: 218241 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3150. Min Act: -0.0001

Data Index: 11193 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.2871. Min Act: -0.0001

Data Index: 553379 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3046. Min Act: -0.0001

Data Index: 1233557 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.2966. Min Act: -0.0001

Data Index: 853334 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.2855. Min Act: -0.0001

Data Index: 1338409 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.2944. Min Act: -0.0001

Data Index: 791628 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.2954. Min Act: -0.0001

Data Index: 62728 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.2430. Min Act: -0.0001

Data Index: 1224769 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.2374. Min Act: -0.0001

Data Index: 1014176 (C4 (Web Text))

Max Activating Token Index: 908