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

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

Neuron 1041 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8571. Min Act: -0.0001

Data Index: 256252 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8809. Min Act: -0.0001

Data Index: 1009876 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8121. Min Act: -0.0001

Data Index: 98027 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7468. Min Act: -0.0001

Data Index: 794971 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8025. Min Act: -0.0001

Data Index: 578918 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7918. Min Act: -0.0001

Data Index: 444098 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8191. Min Act: -0.0001

Data Index: 934367 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7516. Min Act: -0.0001

Data Index: 551270 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7804. Min Act: -0.0001

Data Index: 124851 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8005. Min Act: -0.0001

Data Index: 901532 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7247. Min Act: -0.0001

Data Index: 1173352 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7556. Min Act: -0.0000

Data Index: 663881 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7244. Min Act: -0.0001

Data Index: 1304290 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7485. Min Act: -0.0001

Data Index: 62165 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7438. Min Act: -0.0000

Data Index: 460929 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7504. Min Act: -0.0000

Data Index: 114663 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7053. Min Act: -0.0001

Data Index: 371967 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6834. Min Act: -0.0000

Data Index: 90959 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6949. Min Act: -0.0001

Data Index: 1295243 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7120. Min Act: -0.0000

Data Index: 969727 (C4 (Web Text))

Max Activating Token Index: 481