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

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

Neuron 1954 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.8144. Min Act: -0.0000

Data Index: 605448 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7432. Min Act: -0.0000

Data Index: 948712 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6504. Min Act: -0.0000

Data Index: 803828 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6300. Min Act: -0.0000

Data Index: 540284 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5849. Min Act: -0.0000

Data Index: 288427 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5793. Min Act: -0.0000

Data Index: 23344 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5213. Min Act: -0.0000

Data Index: 885542 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5803. Min Act: -0.0000

Data Index: 20557 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5541. Min Act: -0.0000

Data Index: 693003 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5809. Min Act: -0.0000

Data Index: 823108 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5379. Min Act: -0.0000

Data Index: 380939 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1288494 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5203. Min Act: -0.0000

Data Index: 387173 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.4949. Min Act: -0.0000

Data Index: 539361 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1120395 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5100. Min Act: -0.0000

Data Index: 165512 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5095. Min Act: -0.0000

Data Index: 780441 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1048507 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1251222 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.4470. Min Act: -0.0000

Data Index: 19262 (C4 (Web Text))

Max Activating Token Index: 231