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

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

Neuron 2062 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.2218. Min Act: -0.0001

Data Index: 793470 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.2247. Min Act: -0.0001

Data Index: 745149 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.2205. Min Act: -0.0001

Data Index: 7284 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.2048. Min Act: -0.0001

Data Index: 312972 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1973. Min Act: -0.0001

Data Index: 621354 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.2051. Min Act: -0.0001

Data Index: 949264 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.2049. Min Act: -0.0001

Data Index: 28458 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1953. Min Act: -0.0001

Data Index: 250672 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1949. Min Act: -0.0001

Data Index: 781120 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1884. Min Act: -0.0001

Data Index: 561929 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1926. Min Act: -0.0001

Data Index: 1167061 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1914. Min Act: -0.0001

Data Index: 439619 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1815. Min Act: -0.0001

Data Index: 358017 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1954. Min Act: -0.0001

Data Index: 1317039 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1889. Min Act: -0.0001

Data Index: 1141543 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1945. Min Act: -0.0001

Data Index: 16878 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1803. Min Act: -0.0001

Data Index: 1348607 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1799. Min Act: -0.0001

Data Index: 1236679 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1908. Min Act: -0.0001

Data Index: 434355 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1487. Min Act: -0.0001

Data Index: 846219 (C4 (Web Text))

Max Activating Token Index: 300