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

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

Neuron 5835 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0569. Min Range: -3.0569

Max Act: 3.0569. Min Act: -0.0000

Data Index: 1061458 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 3.0569. Min Range: -3.0569

Max Act: 2.4021. Min Act: -0.0000

Data Index: 904943 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 3.0569. Min Range: -3.0569

Max Act: 2.2703. Min Act: -0.0000

Data Index: 5084 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 3.0569. Min Range: -3.0569

Max Act: 2.2619. Min Act: -0.0000

Data Index: 326432 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 3.0569. Min Range: -3.0569

Max Act: 2.1220. Min Act: -0.0000

Data Index: 522587 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 3.0569. Min Range: -3.0569

Max Act: 2.2219. Min Act: -0.0000

Data Index: 895792 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 3.0569. Min Range: -3.0569

Max Act: 2.0063. Min Act: -0.0000

Data Index: 1017956 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 3.0569. Min Range: -3.0569

Max Act: 2.0919. Min Act: -0.0000

Data Index: 589597 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 3.0569. Min Range: -3.0569

Max Act: 2.1696. Min Act: -0.0000

Data Index: 978028 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 3.0569. Min Range: -3.0569

Max Act: 1.9717. Min Act: -0.0000

Data Index: 87069 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 3.0569. Min Range: -3.0569

Max Act: 2.0573. Min Act: -0.0000

Data Index: 1105026 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 3.0569. Min Range: -3.0569

Max Act: 1.8249. Min Act: -0.0000

Data Index: 993331 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 3.0569. Min Range: -3.0569

Max Act: 1.8160. Min Act: -0.0000

Data Index: 388231 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 3.0569. Min Range: -3.0569

Max Act: 1.9073. Min Act: -0.0000

Data Index: 953929 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 3.0569. Min Range: -3.0569

Max Act: 2.0313. Min Act: -0.0000

Data Index: 144850 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 3.0569. Min Range: -3.0569

Max Act: 1.8262. Min Act: -0.0000

Data Index: 856093 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 3.0569. Min Range: -3.0569

Max Act: 1.7252. Min Act: -0.0000

Data Index: 646233 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 3.0569. Min Range: -3.0569

Max Act: 1.7163. Min Act: -0.0000

Data Index: 336285 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 3.0569. Min Range: -3.0569

Max Act: 1.9124. Min Act: -0.0000

Data Index: 610407 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 3.0569. Min Range: -3.0569

Max Act: 1.7529. Min Act: -0.0000

Data Index: 635044 (C4 (Web Text))

Max Activating Token Index: 786