Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 681 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0003

Data Index: 1079710 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0553. Min Act: -0.0003

Data Index: 25330 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0535. Min Act: -0.0004

Data Index: 1168437 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1178769 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0517. Min Act: -0.0003

Data Index: 846403 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1001134 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1090231 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0477. Min Act: -0.0003

Data Index: 286680 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0461. Min Act: -0.0004

Data Index: 889031 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0468. Min Act: -0.0003

Data Index: 995226 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0484. Min Act: -0.0003

Data Index: 1259978 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0456. Min Act: -0.0003

Data Index: 747472 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0462. Min Act: -0.0003

Data Index: 625313 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0465. Min Act: -0.0003

Data Index: 60081 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1178681 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1009281 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0458. Min Act: -0.0003

Data Index: 554654 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0452. Min Act: -0.0003

Data Index: 965196 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0448. Min Act: -0.0003

Data Index: 892233 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0443. Min Act: -0.0003

Data Index: 1062616 (C4 (Web Text))

Max Activating Token Index: 794