Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 485 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1126. Min Act: -0.0000

Data Index: 122286 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0797. Min Act: -0.0000

Data Index: 344863 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0691. Min Act: -0.0000

Data Index: 923313 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0642. Min Act: -0.0000

Data Index: 117361 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0578. Min Act: -0.0000

Data Index: 947512 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0604. Min Act: -0.0000

Data Index: 599804 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0573. Min Act: -0.0000

Data Index: 1309379 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0565. Min Act: -0.0000

Data Index: 995447 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0581. Min Act: -0.0000

Data Index: 618012 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0539. Min Act: -0.0000

Data Index: 540242 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1087021 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0531. Min Act: -0.0000

Data Index: 267590 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1285077 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0564. Min Act: -0.0001

Data Index: 1170046 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0545. Min Act: -0.0000

Data Index: 722280 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0545. Min Act: -0.0001

Data Index: 832791 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0544. Min Act: -0.0000

Data Index: 296626 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0549. Min Act: -0.0000

Data Index: 230158 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1315572 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0525. Min Act: -0.0000

Data Index: 1168015 (C4 (Web Text))

Max Activating Token Index: 692