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

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

Neuron 3066 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7892. Min Act: -0.0001

Data Index: 165454 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7333. Min Act: -0.0001

Data Index: 661835 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7138. Min Act: -0.0001

Data Index: 48628 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7143. Min Act: -0.0001

Data Index: 1196054 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6942. Min Act: -0.0001

Data Index: 780933 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7249. Min Act: -0.0001

Data Index: 342848 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6769. Min Act: -0.0001

Data Index: 918591 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.7242. Min Act: -0.0001

Data Index: 851117 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6778. Min Act: -0.0001

Data Index: 938314 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6599. Min Act: -0.0001

Data Index: 837977 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6569. Min Act: -0.0001

Data Index: 549488 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6308. Min Act: -0.0001

Data Index: 418831 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6664. Min Act: -0.0001

Data Index: 13209 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6477. Min Act: -0.0001

Data Index: 721277 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6875. Min Act: -0.0001

Data Index: 251820 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6383. Min Act: -0.0001

Data Index: 1038733 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6560. Min Act: -0.0001

Data Index: 1248224 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6289. Min Act: -0.0001

Data Index: 1207552 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6330. Min Act: -0.0001

Data Index: 869898 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.7892. Min Range: -0.7892

Max Act: 0.6518. Min Act: -0.0001

Data Index: 559816 (C4 (Web Text))

Max Activating Token Index: 491