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

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

Neuron 4500 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.3026. Min Act: -0.0000

Data Index: 889848 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.3151. Min Act: -0.0000

Data Index: 286393 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1227848 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1228731 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2194. Min Act: -0.0000

Data Index: 555211 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2112. Min Act: -0.0000

Data Index: 15001 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2199. Min Act: -0.0000

Data Index: 471638 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2221. Min Act: -0.0000

Data Index: 478685 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1074408 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2118. Min Act: -0.0000

Data Index: 212462 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1261772 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1099251 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2104. Min Act: -0.0000

Data Index: 1213060 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2058. Min Act: -0.0000

Data Index: 689978 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2036. Min Act: -0.0000

Data Index: 107887 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2094. Min Act: -0.0000

Data Index: 974180 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1948. Min Act: -0.0000

Data Index: 571854 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2044. Min Act: -0.0000

Data Index: 29939 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2083. Min Act: -0.0000

Data Index: 620638 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1858. Min Act: -0.0000

Data Index: 845789 (C4 (Web Text))

Max Activating Token Index: 883