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

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

Neuron 5060 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2759. Min Act: -0.0000

Data Index: 322732 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2555. Min Act: -0.0000

Data Index: 863235 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1135064 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2308. Min Act: -0.0000

Data Index: 278911 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2308. Min Act: -0.0000

Data Index: 929400 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2044. Min Act: -0.0000

Data Index: 690546 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2245. Min Act: -0.0000

Data Index: 257593 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2154. Min Act: -0.0000

Data Index: 314269 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1320814 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1094351 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1957. Min Act: -0.0000

Data Index: 969366 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1020424 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2064. Min Act: -0.0000

Data Index: 356331 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1897. Min Act: -0.0000

Data Index: 562947 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1867. Min Act: -0.0000

Data Index: 917925 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1179228 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1903. Min Act: -0.0000

Data Index: 452469 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1184300 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1847. Min Act: -0.0000

Data Index: 44556 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1844. Min Act: -0.0000

Data Index: 129980 (C4 (Web Text))

Max Activating Token Index: 125