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

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

Neuron 2375 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1048480 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1170088 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1027840 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.5092. Min Act: -0.0000

Data Index: 82222 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1165983 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1256804 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4862. Min Act: -0.0000

Data Index: 539295 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4667. Min Act: -0.0000

Data Index: 25950 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4321. Min Act: -0.0000

Data Index: 375234 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1069139 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1211858 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4121. Min Act: -0.0000

Data Index: 233865 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1172049 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4287. Min Act: -0.0000

Data Index: 2640 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1085478 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1287785 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.3951. Min Act: -0.0000

Data Index: 857312 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.3857. Min Act: -0.0000

Data Index: 382929 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.3975. Min Act: -0.0000

Data Index: 918423 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.5951. Min Range: -0.5951

Max Act: 0.3959. Min Act: -0.0000

Data Index: 191110 (C4 (Web Text))

Max Activating Token Index: 1003