Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 820 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4788. Min Act: -0.0001

Data Index: 1400700 (Python Code)

Max Activating Token Index: 238

Text #1

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4424. Min Act: -0.0001

Data Index: 1534718 (Python Code)

Max Activating Token Index: 501

Text #2

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4675. Min Act: -0.0001

Data Index: 1467851 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4176. Min Act: -0.0001

Data Index: 1405621 (Python Code)

Max Activating Token Index: 296

Text #4

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4470. Min Act: -0.0001

Data Index: 1383491 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4399. Min Act: -0.0000

Data Index: 1494467 (Python Code)

Max Activating Token Index: 56

Text #6

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1415406 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4247. Min Act: -0.0001

Data Index: 1528853 (Python Code)

Max Activating Token Index: 946

Text #8

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4245. Min Act: -0.0001

Data Index: 1442842 (Python Code)

Max Activating Token Index: 93

Text #9

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1649953 (Python Code)

Max Activating Token Index: 673

Text #10

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4209. Min Act: -0.0001

Data Index: 1386928 (Python Code)

Max Activating Token Index: 391

Text #11

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3941. Min Act: -0.0001

Data Index: 1588632 (Python Code)

Max Activating Token Index: 224

Text #12

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4181. Min Act: -0.0001

Data Index: 1513253 (Python Code)

Max Activating Token Index: 794

Text #13

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4425. Min Act: -0.0001

Data Index: 1518595 (Python Code)

Max Activating Token Index: 562

Text #14

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4162. Min Act: -0.0001

Data Index: 1416260 (Python Code)

Max Activating Token Index: 951

Text #15

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4143. Min Act: -0.0001

Data Index: 1465355 (Python Code)

Max Activating Token Index: 595

Text #16

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3808. Min Act: -0.0001

Data Index: 1555214 (Python Code)

Max Activating Token Index: 361

Text #17

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4032. Min Act: -0.0001

Data Index: 1483449 (Python Code)

Max Activating Token Index: 231

Text #18

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3892. Min Act: -0.0001

Data Index: 1193723 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4020. Min Act: -0.0001

Data Index: 1543263 (Python Code)

Max Activating Token Index: 714