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

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

Neuron 4692 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5980. Min Range: -2.5980

Max Act: 2.5980. Min Act: -0.0000

Data Index: 262461 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 2.5980. Min Range: -2.5980

Max Act: 2.3292. Min Act: -0.0000

Data Index: 974563 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 2.5980. Min Range: -2.5980

Max Act: 2.3052. Min Act: -0.0000

Data Index: 17906 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 2.5980. Min Range: -2.5980

Max Act: 2.1187. Min Act: -0.0000

Data Index: 969249 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 2.5980. Min Range: -2.5980

Max Act: 2.1794. Min Act: -0.0000

Data Index: 551677 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 2.5980. Min Range: -2.5980

Max Act: 2.2356. Min Act: -0.0000

Data Index: 31067 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 2.5980. Min Range: -2.5980

Max Act: 2.2050. Min Act: -0.0000

Data Index: 849151 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 2.5980. Min Range: -2.5980

Max Act: 2.1992. Min Act: -0.0000

Data Index: 625372 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 2.5980. Min Range: -2.5980

Max Act: 2.2833. Min Act: -0.0000

Data Index: 319120 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 2.5980. Min Range: -2.5980

Max Act: 2.1655. Min Act: -0.0000

Data Index: 1058455 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 2.5980. Min Range: -2.5980

Max Act: 1.9730. Min Act: -0.0000

Data Index: 200024 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 2.5980. Min Range: -2.5980

Max Act: 2.0069. Min Act: -0.0000

Data Index: 698173 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 2.5980. Min Range: -2.5980

Max Act: 1.9595. Min Act: -0.0000

Data Index: 427672 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 2.5980. Min Range: -2.5980

Max Act: 1.9704. Min Act: -0.0000

Data Index: 335739 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 2.5980. Min Range: -2.5980

Max Act: 2.0816. Min Act: -0.0000

Data Index: 1227762 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 2.5980. Min Range: -2.5980

Max Act: 1.9733. Min Act: -0.0000

Data Index: 1230389 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 2.5980. Min Range: -2.5980

Max Act: 2.0060. Min Act: -0.0000

Data Index: 1185950 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 2.5980. Min Range: -2.5980

Max Act: 1.9578. Min Act: -0.0000

Data Index: 1203495 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 2.5980. Min Range: -2.5980

Max Act: 1.8541. Min Act: -0.0000

Data Index: 919335 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 2.5980. Min Range: -2.5980

Max Act: 1.9632. Min Act: -0.0000

Data Index: 1207471 (C4 (Web Text))

Max Activating Token Index: 511