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

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

Neuron 1780 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.8067. Min Act: -0.0000

Data Index: 1058192 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.2197. Min Act: -0.0001

Data Index: 722505 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.1952. Min Act: -0.0000

Data Index: 182762 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.1944. Min Act: -0.0000

Data Index: 936257 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.3373. Min Act: -0.0000

Data Index: 947944 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.1873. Min Act: -0.0000

Data Index: 702137 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.1922. Min Act: -0.0000

Data Index: 804932 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1319194 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.1680. Min Act: -0.0000

Data Index: 940447 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.1049. Min Act: -0.0000

Data Index: 184087 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.0252. Min Act: -0.0000

Data Index: 634263 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.1733. Min Act: -0.0000

Data Index: 193185 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1181229 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.0409. Min Act: -0.0000

Data Index: 429780 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.0577. Min Act: -0.0000

Data Index: 119500 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.8067. Min Range: -1.8067

Max Act: 0.9670. Min Act: -0.0000

Data Index: 17044 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 1.8067. Min Range: -1.8067

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1211784 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 1.8067. Min Range: -1.8067

Max Act: 0.9848. Min Act: -0.0000

Data Index: 111231 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 1.8067. Min Range: -1.8067

Max Act: 0.9556. Min Act: -0.0000

Data Index: 38032 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 1.8067. Min Range: -1.8067

Max Act: 0.9189. Min Act: -0.0000

Data Index: 1137927 (C4 (Web Text))

Max Activating Token Index: 704