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

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

Neuron 2896 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1499. Min Act: -0.0001

Data Index: 1333270 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1142. Min Act: -0.0001

Data Index: 684972 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1133. Min Act: -0.0001

Data Index: 939192 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.1058. Min Act: -0.0001

Data Index: 219779 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0981. Min Act: -0.0000

Data Index: 385345 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0964. Min Act: -0.0001

Data Index: 992760 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1270759 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0955. Min Act: -0.0001

Data Index: 671494 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0885. Min Act: -0.0001

Data Index: 570556 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1010255 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0877. Min Act: -0.0001

Data Index: 267605 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0877. Min Act: -0.0001

Data Index: 42153 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1293310 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0890. Min Act: -0.0001

Data Index: 469626 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1206159 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0934. Min Act: -0.0001

Data Index: 772694 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0841. Min Act: -0.0000

Data Index: 1264209 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1137238 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1218949 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.1499. Min Range: -0.1499

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1118842 (C4 (Web Text))

Max Activating Token Index: 611