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

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

Neuron 3075 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0043. Min Range: -3.0043

Max Act: 3.0043. Min Act: 0.0000

Data Index: 287794 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 3.0043. Min Range: -3.0043

Max Act: 2.9296. Min Act: -0.0000

Data Index: 347385 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 3.0043. Min Range: -3.0043

Max Act: 2.2244. Min Act: -0.0000

Data Index: 342687 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 3.0043. Min Range: -3.0043

Max Act: 2.3913. Min Act: -0.0000

Data Index: 465417 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 3.0043. Min Range: -3.0043

Max Act: 2.2936. Min Act: -0.0000

Data Index: 354933 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 3.0043. Min Range: -3.0043

Max Act: 2.0344. Min Act: -0.0000

Data Index: 140530 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 3.0043. Min Range: -3.0043

Max Act: 2.1062. Min Act: -0.0000

Data Index: 1142944 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 3.0043. Min Range: -3.0043

Max Act: 2.2158. Min Act: -0.0000

Data Index: 1253565 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 3.0043. Min Range: -3.0043

Max Act: 2.1975. Min Act: -0.0000

Data Index: 120753 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 3.0043. Min Range: -3.0043

Max Act: 2.1981. Min Act: -0.0000

Data Index: 1174126 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 3.0043. Min Range: -3.0043

Max Act: 2.0865. Min Act: -0.0000

Data Index: 988988 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 3.0043. Min Range: -3.0043

Max Act: 2.0760. Min Act: -0.0000

Data Index: 772240 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 3.0043. Min Range: -3.0043

Max Act: 2.0068. Min Act: -0.0000

Data Index: 178036 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 3.0043. Min Range: -3.0043

Max Act: 1.8949. Min Act: -0.0000

Data Index: 865491 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 3.0043. Min Range: -3.0043

Max Act: 1.9715. Min Act: -0.0000

Data Index: 1217253 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 3.0043. Min Range: -3.0043

Max Act: 1.9137. Min Act: -0.0000

Data Index: 414166 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 3.0043. Min Range: -3.0043

Max Act: 1.8989. Min Act: -0.0000

Data Index: 977520 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 3.0043. Min Range: -3.0043

Max Act: 1.8915. Min Act: -0.0000

Data Index: 272942 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 3.0043. Min Range: -3.0043

Max Act: 1.9648. Min Act: -0.0000

Data Index: 1182451 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 3.0043. Min Range: -3.0043

Max Act: 1.9413. Min Act: -0.0000

Data Index: 1195043 (C4 (Web Text))

Max Activating Token Index: 745