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

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

Neuron 3356 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: 1.8453. Min Range: -1.8453

Max Act: 1.8083. Min Act: -0.0000

Data Index: 66722 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.8453. Min Act: -0.0000

Data Index: 702315 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.8135. Min Act: -0.0000

Data Index: 603916 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.8117. Min Act: -0.0000

Data Index: 729761 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.7827. Min Act: -0.0000

Data Index: 556925 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.8017. Min Act: -0.0000

Data Index: 1030512 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.7881. Min Act: -0.0000

Data Index: 479314 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.7876. Min Act: -0.0000

Data Index: 988243 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.7635. Min Act: -0.0000

Data Index: 892779 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.6633. Min Act: -0.0000

Data Index: 724081 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.7380. Min Act: -0.0000

Data Index: 97827 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.7371. Min Act: -0.0000

Data Index: 335760 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.8252. Min Act: -0.0000

Data Index: 993145 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.7082. Min Act: -0.0000

Data Index: 162390 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.8102. Min Act: -0.0000

Data Index: 440456 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.8026. Min Act: -0.0000

Data Index: 1196036 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.6870. Min Act: -0.0000

Data Index: 1259789 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.6787. Min Act: -0.0000

Data Index: 894106 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.5867. Min Act: -0.0000

Data Index: 540668 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.6712. Min Act: -0.0000

Data Index: 890261 (C4 (Web Text))

Max Activating Token Index: 7