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

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

Neuron 1140 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: 0.4744. Min Range: -0.4744

Max Act: 0.4744. Min Act: -0.0000

Data Index: 859292 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.4100. Min Act: -0.0000

Data Index: 302305 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.3984. Min Act: -0.0000

Data Index: 1231249 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.4102. Min Act: -0.0000

Data Index: 640029 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.3812. Min Act: -0.0000

Data Index: 437685 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.3649. Min Act: -0.0000

Data Index: 833456 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1168371 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.3428. Min Act: -0.0000

Data Index: 809964 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.3268. Min Act: -0.0000

Data Index: 234125 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.3026. Min Act: -0.0000

Data Index: 172020 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1040761 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.3192. Min Act: -0.0000

Data Index: 329936 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.2936. Min Act: -0.0000

Data Index: 197160 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.3197. Min Act: -0.0000

Data Index: 557661 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1255638 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.2922. Min Act: -0.0000

Data Index: 846083 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1195223 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1008325 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.2808. Min Act: -0.0000

Data Index: 249058 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.4744. Min Range: -0.4744

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1233162 (C4 (Web Text))

Max Activating Token Index: 290