Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 371 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0541. Min Act: -0.0003

Data Index: 538288 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0555. Min Act: -0.0003

Data Index: 193360 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0533. Min Act: -0.0003

Data Index: 51669 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0569. Min Act: -0.0003

Data Index: 445877 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0556. Min Act: -0.0004

Data Index: 817943 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0530. Min Act: -0.0003

Data Index: 4245 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1173380 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0521. Min Act: -0.0003

Data Index: 1170080 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0510. Min Act: -0.0003

Data Index: 540613 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0500. Min Act: -0.0003

Data Index: 283666 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0510. Min Act: -0.0003

Data Index: 664212 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0511. Min Act: -0.0003

Data Index: 805409 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0511. Min Act: -0.0003

Data Index: 239952 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1142365 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0506. Min Act: -0.0003

Data Index: 1209567 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0522. Min Act: -0.0003

Data Index: 915089 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0496. Min Act: -0.0003

Data Index: 834714 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0510. Min Act: -0.0003

Data Index: 364249 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1267759 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0489. Min Act: -0.0003

Data Index: 492663 (C4 (Web Text))

Max Activating Token Index: 938