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

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

Neuron 1819 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.3344. Min Act: -0.0003

Data Index: 153024 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2396. Min Act: -0.0003

Data Index: 1061902 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2229. Min Act: -0.0003

Data Index: 1080235 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2262. Min Act: -0.0003

Data Index: 1250340 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2137. Min Act: -0.0003

Data Index: 1066352 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.1977. Min Act: -0.0003

Data Index: 794156 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2060. Min Act: -0.0003

Data Index: 832784 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2210. Min Act: -0.0003

Data Index: 405278 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2262. Min Act: -0.0003

Data Index: 8379 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2036. Min Act: -0.0003

Data Index: 336055 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2134. Min Act: -0.0003

Data Index: 562675 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2052. Min Act: -0.0003

Data Index: 771332 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2309. Min Act: -0.0003

Data Index: 258292 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2070. Min Act: -0.0003

Data Index: 1008705 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.1923. Min Act: -0.0003

Data Index: 947151 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2081. Min Act: -0.0003

Data Index: 1149369 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.1989. Min Act: -0.0003

Data Index: 1183328 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2061. Min Act: -0.0003

Data Index: 515935 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2082. Min Act: -0.0003

Data Index: 777874 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2066. Min Act: -0.0003

Data Index: 898804 (C4 (Web Text))

Max Activating Token Index: 326