Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 83 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.6051. Min Act: -0.0002

Data Index: 86648 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5996. Min Act: -0.0002

Data Index: 1230733 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.6030. Min Act: -0.0002

Data Index: 89600 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.6127. Min Act: -0.0001

Data Index: 1336607 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5968. Min Act: -0.0001

Data Index: 34481 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5943. Min Act: -0.0002

Data Index: 992875 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5741. Min Act: -0.0001

Data Index: 747272 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.6050. Min Act: -0.0001

Data Index: 1215901 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5595. Min Act: -0.0001

Data Index: 717503 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5354. Min Act: -0.0001

Data Index: 343910 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5638. Min Act: -0.0001

Data Index: 899283 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5558. Min Act: -0.0001

Data Index: 761942 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5896. Min Act: -0.0001

Data Index: 643926 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5162. Min Act: -0.0001

Data Index: 851797 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5343. Min Act: -0.0001

Data Index: 1254626 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5920. Min Act: -0.0001

Data Index: 152278 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5122. Min Act: -0.0001

Data Index: 96453 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5305. Min Act: -0.0002

Data Index: 590790 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4849. Min Act: -0.0002

Data Index: 404385 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.5380. Min Act: -0.0002

Data Index: 1043859 (C4 (Web Text))

Max Activating Token Index: 61