Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1848 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.3120. Min Act: -0.0001

Data Index: 306055 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2373. Min Act: -0.0001

Data Index: 1332272 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2250. Min Act: -0.0001

Data Index: 370802 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2397. Min Act: -0.0001

Data Index: 76985 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2252. Min Act: -0.0001

Data Index: 834628 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2015. Min Act: -0.0001

Data Index: 1303539 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2142. Min Act: -0.0001

Data Index: 103091 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2101. Min Act: -0.0001

Data Index: 402525 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2188. Min Act: -0.0001

Data Index: 928816 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2194. Min Act: -0.0001

Data Index: 14254 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2156. Min Act: -0.0001

Data Index: 748270 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2150. Min Act: -0.0001

Data Index: 108648 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2057. Min Act: -0.0001

Data Index: 738444 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.1960. Min Act: -0.0001

Data Index: 689452 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2027. Min Act: -0.0001

Data Index: 1280620 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2073. Min Act: -0.0001

Data Index: 862633 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2075. Min Act: -0.0001

Data Index: 129096 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.1990. Min Act: -0.0001

Data Index: 947225 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2037. Min Act: -0.0001

Data Index: 398783 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.3120. Min Range: -0.3120

Max Act: 0.2092. Min Act: -0.0001

Data Index: 481891 (C4 (Web Text))

Max Activating Token Index: 749