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

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

Neuron 4165 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: 6.1292. Min Range: -6.1292

Max Act: 6.1292. Min Act: -0.0000

Data Index: 1234976 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 6.1292. Min Range: -6.1292

Max Act: 5.6368. Min Act: -0.0000

Data Index: 93657 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 6.1292. Min Range: -6.1292

Max Act: 5.3588. Min Act: -0.0000

Data Index: 1054472 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.8705. Min Act: -0.0000

Data Index: 1297244 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.9747. Min Act: -0.0000

Data Index: 1248294 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.7555. Min Act: -0.0000

Data Index: 531207 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.8518. Min Act: -0.0000

Data Index: 935397 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.8371. Min Act: -0.0000

Data Index: 895176 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.7926. Min Act: -0.0000

Data Index: 84472 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.6270. Min Act: -0.0000

Data Index: 1052797 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.5827. Min Act: -0.0000

Data Index: 397170 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.7529. Min Act: -0.0000

Data Index: 180555 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.7795. Min Act: -0.0000

Data Index: 376181 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.7343. Min Act: -0.0000

Data Index: 200466 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.7359. Min Act: -0.0000

Data Index: 1321004 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.6342. Min Act: -0.0000

Data Index: 440203 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.8024. Min Act: -0.0000

Data Index: 1069596 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.5908. Min Act: -0.0000

Data Index: 1067175 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.4039. Min Act: -0.0000

Data Index: 1093618 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 6.1292. Min Range: -6.1292

Max Act: 4.5406. Min Act: -0.0000

Data Index: 996536 (C4 (Web Text))

Max Activating Token Index: 545