Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2190 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.5507. Min Act: -0.0000

Data Index: 769537 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.5195. Min Act: -0.0000

Data Index: 620598 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.4780. Min Act: -0.0001

Data Index: 348028 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.5067. Min Act: -0.0001

Data Index: 592823 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.4565. Min Act: -0.0001

Data Index: 790096 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.4231. Min Act: -0.0001

Data Index: 539298 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3935. Min Act: -0.0001

Data Index: 895731 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3997. Min Act: -0.0001

Data Index: 482061 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.4283. Min Act: -0.0001

Data Index: 211367 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3916. Min Act: -0.0000

Data Index: 444846 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3877. Min Act: -0.0001

Data Index: 397172 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.4129. Min Act: -0.0000

Data Index: 674268 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3990. Min Act: -0.0001

Data Index: 801801 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3928. Min Act: -0.0001

Data Index: 105115 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3699. Min Act: -0.0001

Data Index: 723112 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3959. Min Act: -0.0001

Data Index: 523504 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1318924 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.4031. Min Act: -0.0001

Data Index: 942211 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1304076 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3877. Min Act: -0.0001

Data Index: 424054 (C4 (Web Text))

Max Activating Token Index: 688