Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 649 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.6590. Min Act: -0.0000

Data Index: 644528 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4579. Min Act: -0.0000

Data Index: 1301316 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4688. Min Act: -0.0001

Data Index: 182889 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5015. Min Act: -0.0000

Data Index: 760901 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1335731 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4349. Min Act: -0.0000

Data Index: 462240 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4533. Min Act: -0.0001

Data Index: 1219932 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4468. Min Act: -0.0000

Data Index: 851229 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4409. Min Act: -0.0000

Data Index: 589596 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4124. Min Act: -0.0000

Data Index: 571924 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4662. Min Act: -0.0000

Data Index: 296711 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4432. Min Act: -0.0000

Data Index: 384278 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.3757. Min Act: -0.0000

Data Index: 250909 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4012. Min Act: -0.0001

Data Index: 1322579 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4377. Min Act: -0.0000

Data Index: 295588 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4198. Min Act: -0.0000

Data Index: 681653 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1246306 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1354684 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4243. Min Act: -0.0001

Data Index: 755736 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.3345. Min Act: -0.0000

Data Index: 1161141 (C4 (Web Text))

Max Activating Token Index: 217