Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1528 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.7209. Min Act: -0.0000

Data Index: 604607 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.6197. Min Act: -0.0000

Data Index: 578236 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.6141. Min Act: -0.0000

Data Index: 60972 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.6523. Min Act: -0.0000

Data Index: 294531 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5826. Min Act: -0.0000

Data Index: 450623 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5900. Min Act: -0.0000

Data Index: 347598 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5807. Min Act: -0.0000

Data Index: 699477 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5578. Min Act: -0.0000

Data Index: 644791 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5187. Min Act: -0.0000

Data Index: 125924 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1121237 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5227. Min Act: -0.0000

Data Index: 158100 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5400. Min Act: -0.0000

Data Index: 411647 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5249. Min Act: -0.0000

Data Index: 733352 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.4989. Min Act: -0.0000

Data Index: 666092 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5110. Min Act: -0.0000

Data Index: 754723 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5821. Min Act: -0.0000

Data Index: 330391 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1345343 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.4799. Min Act: -0.0000

Data Index: 496086 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.4755. Min Act: -0.0000

Data Index: 76477 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.7209. Min Range: -0.7209

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1080842 (C4 (Web Text))

Max Activating Token Index: 497