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

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

Neuron 3259 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.5179. Min Act: -0.0002

Data Index: 1076591 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4774. Min Act: -0.0002

Data Index: 1125534 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4748. Min Act: -0.0002

Data Index: 290043 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4642. Min Act: -0.0002

Data Index: 877611 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4286. Min Act: -0.0002

Data Index: 1065334 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4575. Min Act: -0.0002

Data Index: 1042525 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4558. Min Act: -0.0002

Data Index: 192697 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4115. Min Act: -0.0002

Data Index: 108123 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4421. Min Act: -0.0002

Data Index: 11844 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4709. Min Act: -0.0002

Data Index: 1176478 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4435. Min Act: -0.0002

Data Index: 443406 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4441. Min Act: -0.0002

Data Index: 602019 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4295. Min Act: -0.0002

Data Index: 813875 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3999. Min Act: -0.0002

Data Index: 27981 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4262. Min Act: -0.0002

Data Index: 1051347 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4291. Min Act: -0.0002

Data Index: 965505 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4437. Min Act: -0.0002

Data Index: 1257657 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4128. Min Act: -0.0002

Data Index: 197543 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4373. Min Act: -0.0002

Data Index: 600215 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4257. Min Act: -0.0002

Data Index: 344747 (C4 (Web Text))

Max Activating Token Index: 223