Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1104 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.1094. Min Act: -0.0004

Data Index: 139254 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0996. Min Act: -0.0003

Data Index: 975453 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0946. Min Act: -0.0003

Data Index: 205348 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0975. Min Act: -0.0003

Data Index: 1111973 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0970. Min Act: -0.0003

Data Index: 1268377 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0981. Min Act: -0.0003

Data Index: 699976 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0934. Min Act: -0.0003

Data Index: 164452 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0924. Min Act: -0.0003

Data Index: 35441 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0901. Min Act: -0.0003

Data Index: 155589 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0903. Min Act: -0.0003

Data Index: 553278 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0887. Min Act: -0.0003

Data Index: 923321 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0885. Min Act: -0.0003

Data Index: 505376 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0850. Min Act: -0.0003

Data Index: 183123 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0850. Min Act: -0.0004

Data Index: 40544 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0847. Min Act: -0.0003

Data Index: 882985 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0871. Min Act: -0.0003

Data Index: 1064663 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0858. Min Act: -0.0004

Data Index: 1258461 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0840. Min Act: -0.0003

Data Index: 1536556 (Python Code)

Max Activating Token Index: 847

Text #18

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0830. Min Act: -0.0003

Data Index: 836030 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0828. Min Act: -0.0003

Data Index: 1265657 (C4 (Web Text))

Max Activating Token Index: 331