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

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

Neuron 2164 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: 1.1294. Min Range: -1.1294

Max Act: 1.1294. Min Act: -0.0003

Data Index: 205252 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.9057. Min Act: -0.0003

Data Index: 76905 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.9167. Min Act: -0.0003

Data Index: 580686 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.7308. Min Act: -0.0003

Data Index: 538711 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.7396. Min Act: -0.0003

Data Index: 230137 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.6914. Min Act: -0.0003

Data Index: 1182381 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.7051. Min Act: -0.0003

Data Index: 1306140 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.5887. Min Act: -0.0003

Data Index: 353437 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.6012. Min Act: -0.0003

Data Index: 637313 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.6154. Min Act: -0.0003

Data Index: 1160267 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.6276. Min Act: -0.0003

Data Index: 1155721 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.6166. Min Act: -0.0003

Data Index: 459766 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.5851. Min Act: -0.0003

Data Index: 457935 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.5968. Min Act: -0.0003

Data Index: 884978 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.6074. Min Act: -0.0003

Data Index: 544056 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.5661. Min Act: -0.0003

Data Index: 1330775 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.5692. Min Act: -0.0003

Data Index: 1317254 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.5640. Min Act: -0.0003

Data Index: 146978 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.5569. Min Act: -0.0003

Data Index: 105643 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.5531. Min Act: -0.0003

Data Index: 45168 (C4 (Web Text))

Max Activating Token Index: 131