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

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

Neuron 48 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1238346 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.7192. Min Act: -0.0000

Data Index: 676719 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6636. Min Act: -0.0000

Data Index: 341036 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1058466 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6425. Min Act: -0.0000

Data Index: 98027 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6449. Min Act: -0.0000

Data Index: 399094 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6725. Min Act: -0.0000

Data Index: 321746 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6802. Min Act: -0.0000

Data Index: 968472 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6252. Min Act: -0.0000

Data Index: 205370 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5545. Min Act: -0.0000

Data Index: 995104 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1208615 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.4783. Min Act: -0.0000

Data Index: 535859 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5758. Min Act: -0.0000

Data Index: 275260 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5758. Min Act: -0.0000

Data Index: 661064 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5127. Min Act: -0.0000

Data Index: 408700 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5417. Min Act: -0.0000

Data Index: 235055 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5524. Min Act: -0.0000

Data Index: 58697 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5159. Min Act: -0.0000

Data Index: 56939 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.4817. Min Act: -0.0000

Data Index: 398749 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5078. Min Act: -0.0000

Data Index: 959037 (C4 (Web Text))

Max Activating Token Index: 723