Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 55 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0891. Min Range: -1.0891

Max Act: 1.0173. Min Act: -0.0001

Data Index: 560711 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.0891. Min Range: -1.0891

Max Act: 1.0891. Min Act: -0.0001

Data Index: 513478 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 1.0891. Min Range: -1.0891

Max Act: 1.0259. Min Act: -0.0000

Data Index: 240457 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.9925. Min Act: -0.0000

Data Index: 863416 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.9410. Min Act: -0.0001

Data Index: 984118 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1055078 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.8887. Min Act: -0.0001

Data Index: 1109195 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.9075. Min Act: -0.0000

Data Index: 898804 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.8798. Min Act: -0.0000

Data Index: 403190 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.8380. Min Act: -0.0000

Data Index: 22346 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.8298. Min Act: -0.0001

Data Index: 1067625 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.8392. Min Act: -0.0000

Data Index: 433400 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7704. Min Act: -0.0000

Data Index: 13007 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1122176 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1310293 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.8279. Min Act: -0.0001

Data Index: 161770 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7761. Min Act: -0.0001

Data Index: 314197 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.6970. Min Act: -0.0001

Data Index: 930216 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7867. Min Act: -0.0000

Data Index: 998947 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7355. Min Act: -0.0000

Data Index: 302190 (C4 (Web Text))

Max Activating Token Index: 41