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

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

Neuron 2538 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1258. Min Act: -0.0000

Data Index: 855288 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1236. Min Act: 0.0000

Data Index: 878494 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1250. Min Act: -0.0000

Data Index: 939119 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1136. Min Act: 0.0000

Data Index: 1224955 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1047. Min Act: -0.0000

Data Index: 285911 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1083. Min Act: 0.0000

Data Index: 1009726 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1045. Min Act: -0.0000

Data Index: 742082 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1011. Min Act: 0.0000

Data Index: 354685 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0983. Min Act: -0.0000

Data Index: 38621 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1080752 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0904. Min Act: 0.0000

Data Index: 796396 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0963. Min Act: -0.0000

Data Index: 117877 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1154518 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0888. Min Act: -0.0000

Data Index: 986232 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0916. Min Act: -0.0000

Data Index: 545732 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0909. Min Act: -0.0000

Data Index: 114816 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0873. Min Act: -0.0000

Data Index: 120781 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0899. Min Act: -0.0000

Data Index: 348267 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0866. Min Act: -0.0000

Data Index: 147073 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0920. Min Act: -0.0000

Data Index: 216821 (C4 (Web Text))

Max Activating Token Index: 52