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

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

Neuron 1711 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.9973. Min Act: -0.0001

Data Index: 1131556 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.8885. Min Act: -0.0001

Data Index: 359314 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7827. Min Act: -0.0001

Data Index: 1460926 (Python Code)

Max Activating Token Index: 761

Text #3

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7828. Min Act: -0.0001

Data Index: 1498286 (Python Code)

Max Activating Token Index: 904

Text #4

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.8952. Min Act: -0.0001

Data Index: 1557467 (Python Code)

Max Activating Token Index: 223

Text #5

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.9009. Min Act: -0.0001

Data Index: 1566108 (Python Code)

Max Activating Token Index: 946

Text #6

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7811. Min Act: -0.0001

Data Index: 214543 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.8006. Min Act: -0.0001

Data Index: 937852 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7672. Min Act: -0.0001

Data Index: 39311 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7383. Min Act: -0.0001

Data Index: 681697 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7787. Min Act: -0.0001

Data Index: 539426 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7695. Min Act: -0.0001

Data Index: 594608 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7761. Min Act: -0.0001

Data Index: 1104903 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7994. Min Act: -0.0001

Data Index: 712750 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7118. Min Act: -0.0001

Data Index: 135547 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6918. Min Act: -0.0001

Data Index: 403929 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7591. Min Act: -0.0001

Data Index: 872242 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.6769. Min Act: -0.0001

Data Index: 304767 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7372. Min Act: -0.0001

Data Index: 961864 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.9973. Min Range: -0.9973

Max Act: 0.7423. Min Act: -0.0001

Data Index: 321950 (C4 (Web Text))

Max Activating Token Index: 902