Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3530 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7794. Min Act: -0.0001

Data Index: 523442 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7931. Min Act: -0.0001

Data Index: 149007 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.8836. Min Act: -0.0001

Data Index: 5161 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6349. Min Act: -0.0001

Data Index: 717777 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7099. Min Act: -0.0001

Data Index: 860113 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6679. Min Act: -0.0001

Data Index: 520648 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6424. Min Act: -0.0001

Data Index: 174449 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6834. Min Act: -0.0001

Data Index: 928696 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7390. Min Act: -0.0001

Data Index: 1085324 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6647. Min Act: -0.0001

Data Index: 863554 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6217. Min Act: -0.0001

Data Index: 198161 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6787. Min Act: -0.0001

Data Index: 681983 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7798. Min Act: -0.0001

Data Index: 511189 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6333. Min Act: -0.0001

Data Index: 1080747 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6560. Min Act: -0.0001

Data Index: 367302 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6349. Min Act: -0.0001

Data Index: 638241 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6085. Min Act: -0.0001

Data Index: 581072 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.8113. Min Act: -0.0001

Data Index: 1155143 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7078. Min Act: -0.0001

Data Index: 313425 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6428. Min Act: -0.0001

Data Index: 1172852 (C4 (Web Text))

Max Activating Token Index: 291