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

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

Neuron 249 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1596. Min Act: -0.0000

Data Index: 763670 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1287. Min Act: -0.0000

Data Index: 581942 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1172. Min Act: -0.0000

Data Index: 25926 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1133. Min Act: -0.0000

Data Index: 93337 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1339110 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1038. Min Act: -0.0000

Data Index: 998585 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1231764 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1054. Min Act: -0.0000

Data Index: 1258161 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1039667 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1061172 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0964. Min Act: -0.0000

Data Index: 166085 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0877. Min Act: -0.0000

Data Index: 562696 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0926. Min Act: -0.0000

Data Index: 783433 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0922. Min Act: -0.0000

Data Index: 149268 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0905. Min Act: -0.0000

Data Index: 499004 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0911. Min Act: -0.0000

Data Index: 638065 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0873. Min Act: -0.0000

Data Index: 224982 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0904. Min Act: -0.0000

Data Index: 800779 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0893. Min Act: -0.0000

Data Index: 879017 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.0882. Min Act: -0.0000

Data Index: 247555 (C4 (Web Text))

Max Activating Token Index: 723