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

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

Neuron 1629 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: 0.5398. Min Range: -0.5398

Max Act: 0.5398. Min Act: -0.0000

Data Index: 661844 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.5276. Min Act: -0.0000

Data Index: 125636 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4886. Min Act: -0.0000

Data Index: 816110 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1343618 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.5246. Min Act: -0.0000

Data Index: 471648 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1199723 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1348941 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4765. Min Act: -0.0000

Data Index: 556902 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4756. Min Act: -0.0000

Data Index: 297310 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1308114 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1071179 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1269132 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4076. Min Act: -0.0000

Data Index: 178172 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4023. Min Act: -0.0000

Data Index: 173123 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4002. Min Act: -0.0000

Data Index: 412205 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1022881 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3948. Min Act: -0.0000

Data Index: 891109 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4059. Min Act: -0.0000

Data Index: 70468 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4211. Min Act: -0.0000

Data Index: 627521 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4102. Min Act: -0.0000

Data Index: 891608 (C4 (Web Text))

Max Activating Token Index: 985