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

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

Neuron 4319 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: 0.7906. Min Range: -0.7906

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1649416 (Python Code)

Max Activating Token Index: 342

Text #1

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1592531 (Python Code)

Max Activating Token Index: 753

Text #2

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7906. Min Act: -0.0000

Data Index: 414129 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1407184 (Python Code)

Max Activating Token Index: 431

Text #4

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1296218 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7883. Min Act: -0.0000

Data Index: 295250 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1002929 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7066. Min Act: -0.0000

Data Index: 995930 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6754. Min Act: -0.0000

Data Index: 517678 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6511. Min Act: -0.0000

Data Index: 307116 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6241. Min Act: -0.0000

Data Index: 57514 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1373209 (Python Code)

Max Activating Token Index: 393

Text #12

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1024546 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1233945 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1164454 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5841. Min Act: -0.0000

Data Index: 62072 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1305682 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6112. Min Act: -0.0000

Data Index: 104547 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1576714 (Python Code)

Max Activating Token Index: 224

Text #19

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5882. Min Act: -0.0000

Data Index: 1429316 (Python Code)

Max Activating Token Index: 266