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

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

Neuron 2113 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: 5.1191. Min Range: -5.1191

Max Act: 5.1191. Min Act: -0.0000

Data Index: 73943 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 5.1191. Min Range: -5.1191

Max Act: 4.5028. Min Act: -0.0000

Data Index: 1596049 (Python Code)

Max Activating Token Index: 329

Text #2

Max Range: 5.1191. Min Range: -5.1191

Max Act: 4.1503. Min Act: -0.0000

Data Index: 1164146 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 5.1191. Min Range: -5.1191

Max Act: 3.7947. Min Act: -0.0000

Data Index: 1589378 (Python Code)

Max Activating Token Index: 531

Text #4

Max Range: 5.1191. Min Range: -5.1191

Max Act: 3.6534. Min Act: -0.0000

Data Index: 644249 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 5.1191. Min Range: -5.1191

Max Act: 3.5011. Min Act: -0.0000

Data Index: 755393 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 5.1191. Min Range: -5.1191

Max Act: 3.0814. Min Act: -0.0000

Data Index: 667917 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 5.1191. Min Range: -5.1191

Max Act: 3.0798. Min Act: -0.0000

Data Index: 1081055 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 5.1191. Min Range: -5.1191

Max Act: 3.3718. Min Act: -0.0000

Data Index: 714294 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 5.1191. Min Range: -5.1191

Max Act: 3.0368. Min Act: -0.0000

Data Index: 743261 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 5.1191. Min Range: -5.1191

Max Act: 2.9453. Min Act: -0.0000

Data Index: 1153089 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 5.1191. Min Range: -5.1191

Max Act: 2.7900. Min Act: -0.0000

Data Index: 1174326 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 5.1191. Min Range: -5.1191

Max Act: 2.7306. Min Act: -0.0000

Data Index: 1339775 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 5.1191. Min Range: -5.1191

Max Act: 2.8601. Min Act: -0.0000

Data Index: 1165340 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 5.1191. Min Range: -5.1191

Max Act: 2.9856. Min Act: -0.0000

Data Index: 852846 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 5.1191. Min Range: -5.1191

Max Act: 2.7257. Min Act: -0.0000

Data Index: 1090016 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 5.1191. Min Range: -5.1191

Max Act: 2.7167. Min Act: -0.0000

Data Index: 107711 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 5.1191. Min Range: -5.1191

Max Act: 2.7254. Min Act: -0.0000

Data Index: 584766 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 5.1191. Min Range: -5.1191

Max Act: 2.5791. Min Act: -0.0000

Data Index: 974585 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 5.1191. Min Range: -5.1191

Max Act: 2.8217. Min Act: -0.0000

Data Index: 696087 (C4 (Web Text))

Max Activating Token Index: 61