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

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

Neuron 1453 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0062. Min Range: -1.0062

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1009684 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.9655. Min Act: -0.0000

Data Index: 737848 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.9777. Min Act: -0.0000

Data Index: 882451 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.9182. Min Act: -0.0000

Data Index: 740280 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1164142 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1272754 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.7569. Min Act: -0.0000

Data Index: 378690 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.8606. Min Act: -0.0000

Data Index: 594608 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.8262. Min Act: -0.0000

Data Index: 927697 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.7832. Min Act: -0.0000

Data Index: 488980 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.8298. Min Act: -0.0000

Data Index: 513915 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.8214. Min Act: -0.0000

Data Index: 574353 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1259076 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.7888. Min Act: -0.0000

Data Index: 331564 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.8042. Min Act: -0.0000

Data Index: 53196 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.7986. Min Act: -0.0000

Data Index: 350929 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.8176. Min Act: -0.0000

Data Index: 354569 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.8239. Min Act: -0.0000

Data Index: 986464 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.7815. Min Act: -0.0000

Data Index: 247231 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 1.0062. Min Range: -1.0062

Max Act: 0.7107. Min Act: -0.0000

Data Index: 647640 (C4 (Web Text))

Max Activating Token Index: 904