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

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

Neuron 2712 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.5206. Min Act: 0.0000

Data Index: 573061 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.4518. Min Act: -0.0000

Data Index: 321858 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.4427. Min Act: -0.0000

Data Index: 304301 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.4210. Min Act: -0.0000

Data Index: 418282 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1349619 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1244346 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.3885. Min Act: -0.0000

Data Index: 196849 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.3867. Min Act: 0.0001

Data Index: 454720 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.4067. Min Act: -0.0000

Data Index: 897272 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.3895. Min Act: -0.0000

Data Index: 712044 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1084066 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.4020. Min Act: -0.0000

Data Index: 552300 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.3808. Min Act: 0.0000

Data Index: 980202 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1012825 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.3820. Min Act: -0.0000

Data Index: 436524 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.3667. Min Act: 0.0000

Data Index: 353114 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.3879. Min Act: -0.0000

Data Index: 703326 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.3621. Min Act: -0.0000

Data Index: 369329 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.3692. Min Act: -0.0000

Data Index: 666453 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.5206. Min Range: -0.5206

Max Act: 0.3544. Min Act: -0.0000

Data Index: 352055 (C4 (Web Text))

Max Activating Token Index: 590