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

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

Neuron 2788 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1006336 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1149078 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1001564 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3124. Min Act: -0.0000

Data Index: 44816 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3025. Min Act: -0.0000

Data Index: 765903 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1220264 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2878. Min Act: -0.0000

Data Index: 338024 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2818. Min Act: -0.0000

Data Index: 62307 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1207336 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2726. Min Act: -0.0000

Data Index: 604134 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2718. Min Act: -0.0000

Data Index: 444963 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2539. Min Act: -0.0000

Data Index: 701373 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2596. Min Act: -0.0000

Data Index: 118532 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2676. Min Act: -0.0000

Data Index: 630324 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2199. Min Act: -0.0000

Data Index: 942617 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2825. Min Act: -0.0000

Data Index: 808411 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2254. Min Act: -0.0000

Data Index: 949109 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1096719 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1235971 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2383. Min Act: -0.0000

Data Index: 973529 (C4 (Web Text))

Max Activating Token Index: 324