Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1089 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.6122. Min Act: -0.0000

Data Index: 1263092 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.3672. Min Act: -0.0000

Data Index: 1018074 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.2417. Min Act: -0.0001

Data Index: 693210 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.3952. Min Act: -0.0000

Data Index: 252193 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.2250. Min Act: -0.0000

Data Index: 884266 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.1417. Min Act: -0.0000

Data Index: 614886 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.3098. Min Act: -0.0000

Data Index: 471263 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.2188. Min Act: -0.0000

Data Index: 674375 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1198056 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.1252. Min Act: -0.0000

Data Index: 226450 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1359231 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.1304. Min Act: -0.0000

Data Index: 326331 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.0976. Min Act: -0.0000

Data Index: 821238 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.1691. Min Act: -0.0000

Data Index: 697563 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.1537. Min Act: -0.0000

Data Index: 911958 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1351914 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.0652. Min Act: -0.0000

Data Index: 249143 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.0033. Min Act: -0.0000

Data Index: 481508 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.0264. Min Act: -0.0000

Data Index: 595064 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 1.6122. Min Range: -1.6122

Max Act: 1.0860. Min Act: -0.0000

Data Index: 96863 (C4 (Web Text))

Max Activating Token Index: 521