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

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

Neuron 2228 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.7329. Min Act: -0.0000

Data Index: 907863 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.8128. Min Act: -0.0000

Data Index: 384961 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.6133. Min Act: -0.0000

Data Index: 957934 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.5987. Min Act: -0.0000

Data Index: 932395 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.4318. Min Act: -0.0000

Data Index: 692621 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.5375. Min Act: -0.0000

Data Index: 1531670 (Python Code)

Max Activating Token Index: 540

Text #6

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.4176. Min Act: -0.0000

Data Index: 256017 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.5235. Min Act: -0.0000

Data Index: 1251969 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.5164. Min Act: -0.0000

Data Index: 1112616 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.3876. Min Act: -0.0000

Data Index: 171745 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.4641. Min Act: -0.0000

Data Index: 802430 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.4761. Min Act: -0.0000

Data Index: 929237 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.5797. Min Act: -0.0000

Data Index: 135349 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.4266. Min Act: -0.0000

Data Index: 123000 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.2891. Min Act: -0.0000

Data Index: 324122 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.4086. Min Act: -0.0000

Data Index: 369298 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.4111. Min Act: -0.0000

Data Index: 1157266 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.1809. Min Act: -0.0000

Data Index: 521496 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.3985. Min Act: -0.0000

Data Index: 6523 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 2.8128. Min Range: -2.8128

Max Act: 2.4006. Min Act: -0.0000

Data Index: 579040 (C4 (Web Text))

Max Activating Token Index: 10