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

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

Neuron 1673 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6554. Min Act: -0.0003

Data Index: 282016 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.5355. Min Act: -0.0003

Data Index: 280867 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.5352. Min Act: -0.0003

Data Index: 1127559 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.5158. Min Act: -0.0002

Data Index: 693537 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.5141. Min Act: -0.0002

Data Index: 231084 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.5073. Min Act: -0.0003

Data Index: 494160 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.5202. Min Act: -0.0003

Data Index: 745926 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.5187. Min Act: -0.0003

Data Index: 358576 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.4975. Min Act: -0.0003

Data Index: 433951 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.5073. Min Act: -0.0003

Data Index: 284696 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.5041. Min Act: -0.0003

Data Index: 1116819 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.5199. Min Act: -0.0002

Data Index: 287172 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.5002. Min Act: -0.0002

Data Index: 593297 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.4962. Min Act: -0.0003

Data Index: 727980 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.4951. Min Act: -0.0002

Data Index: 1318531 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.4744. Min Act: -0.0003

Data Index: 583682 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.4939. Min Act: -0.0003

Data Index: 547755 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.4784. Min Act: -0.0003

Data Index: 50327 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.4784. Min Act: -0.0003

Data Index: 536563 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.4915. Min Act: -0.0002

Data Index: 441999 (C4 (Web Text))

Max Activating Token Index: 421