Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2400 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0781. Min Act: -0.0001

Data Index: 991157 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0815. Min Act: -0.0001

Data Index: 712321 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0781. Min Act: -0.0001

Data Index: 176902 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0747. Min Act: -0.0001

Data Index: 772063 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1232752 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0693. Min Act: -0.0001

Data Index: 624347 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0667. Min Act: -0.0001

Data Index: 408166 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0664. Min Act: 0.0000

Data Index: 1006182 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0661. Min Act: -0.0001

Data Index: 71424 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0614. Min Act: -0.0001

Data Index: 270305 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1274243 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0637. Min Act: -0.0001

Data Index: 640527 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0630. Min Act: -0.0001

Data Index: 38282 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0655. Min Act: -0.0001

Data Index: 183623 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1321250 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0638. Min Act: 0.0000

Data Index: 1342386 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1190652 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0621. Min Act: -0.0000

Data Index: 432696 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1197277 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0604. Min Act: -0.0001

Data Index: 330663 (C4 (Web Text))

Max Activating Token Index: 561