Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1316 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.1382. Min Act: -0.0001

Data Index: 561909 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.1849. Min Act: -0.0001

Data Index: 655130 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0866. Min Act: -0.0001

Data Index: 766705 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0576. Min Act: -0.0001

Data Index: 95409 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9621. Min Act: -0.0001

Data Index: 187357 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0357. Min Act: -0.0001

Data Index: 22919 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9828. Min Act: -0.0001

Data Index: 1324759 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9362. Min Act: -0.0001

Data Index: 958325 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.7524. Min Act: -0.0001

Data Index: 508127 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9441. Min Act: -0.0001

Data Index: 1255690 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0068. Min Act: -0.0001

Data Index: 316629 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9348. Min Act: -0.0001

Data Index: 1027861 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0757. Min Act: -0.0001

Data Index: 631181 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9369. Min Act: -0.0001

Data Index: 246014 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8768. Min Act: -0.0001

Data Index: 980400 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0435. Min Act: -0.0001

Data Index: 649687 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8878. Min Act: -0.0001

Data Index: 889067 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8885. Min Act: -0.0001

Data Index: 425711 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8620. Min Act: -0.0001

Data Index: 333357 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.8174. Min Act: -0.0001

Data Index: 1279172 (C4 (Web Text))

Max Activating Token Index: 348