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

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

Neuron 532 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: 0.0640. Min Range: -0.0640

Max Act: 0.0640. Min Act: -0.0003

Data Index: 930880 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0631. Min Act: -0.0003

Data Index: 457737 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1289807 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0599. Min Act: -0.0003

Data Index: 91630 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0603. Min Act: -0.0003

Data Index: 828624 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0598. Min Act: -0.0003

Data Index: 847498 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0603. Min Act: -0.0003

Data Index: 413235 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0589. Min Act: -0.0003

Data Index: 496291 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0579. Min Act: -0.0003

Data Index: 1346517 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0582. Min Act: -0.0003

Data Index: 746037 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0587. Min Act: -0.0003

Data Index: 456607 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0584. Min Act: -0.0003

Data Index: 596083 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0591. Min Act: -0.0003

Data Index: 732993 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0567. Min Act: -0.0003

Data Index: 692046 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1199726 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0567. Min Act: -0.0003

Data Index: 122893 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0574. Min Act: -0.0003

Data Index: 338866 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0570. Min Act: -0.0003

Data Index: 438082 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1277023 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0572. Min Act: -0.0003

Data Index: 320361 (C4 (Web Text))

Max Activating Token Index: 138