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

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

Neuron 3077 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: 0.8095. Min Range: -0.8095

Max Act: 0.8095. Min Act: -0.0000

Data Index: 324307 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5373. Min Act: -0.0001

Data Index: 393499 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5417. Min Act: -0.0001

Data Index: 1350856 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4973. Min Act: -0.0000

Data Index: 599330 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4246. Min Act: -0.0001

Data Index: 580416 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4571. Min Act: -0.0001

Data Index: 117387 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4591. Min Act: -0.0001

Data Index: 172020 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4100. Min Act: -0.0000

Data Index: 917611 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4174. Min Act: -0.0001

Data Index: 64404 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4138. Min Act: -0.0000

Data Index: 628776 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4403. Min Act: -0.0001

Data Index: 642338 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4129. Min Act: -0.0001

Data Index: 219782 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4226. Min Act: -0.0000

Data Index: 963567 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1172566 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4432. Min Act: -0.0001

Data Index: 119110 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.3703. Min Act: -0.0001

Data Index: 787601 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4153. Min Act: -0.0000

Data Index: 341225 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4209. Min Act: -0.0001

Data Index: 194043 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4027. Min Act: -0.0001

Data Index: 1164997 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4255. Min Act: -0.0001

Data Index: 1181854 (C4 (Web Text))

Max Activating Token Index: 455