Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 607 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.9011. Min Act: -0.0000

Data Index: 519635 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.9458. Min Act: -0.0000

Data Index: 1150197 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.7839. Min Act: -0.0000

Data Index: 706161 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.8627. Min Act: -0.0000

Data Index: 1242644 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.8220. Min Act: -0.0000

Data Index: 1166502 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.5745. Min Act: -0.0000

Data Index: 201305 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.7538. Min Act: -0.0000

Data Index: 631960 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.5296. Min Act: -0.0000

Data Index: 86040 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.5016. Min Act: -0.0000

Data Index: 540644 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.5851. Min Act: -0.0000

Data Index: 1029287 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.4837. Min Act: -0.0000

Data Index: 1215045 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.4923. Min Act: -0.0000

Data Index: 918568 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.4224. Min Act: -0.0000

Data Index: 1266051 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.1386. Min Act: -0.0000

Data Index: 680028 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.1499. Min Act: -0.0000

Data Index: 309051 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.1511. Min Act: -0.0000

Data Index: 749023 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.1446. Min Act: -0.0000

Data Index: 1217220 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.1785. Min Act: -0.0000

Data Index: 21678 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1294953 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 1.9458. Min Range: -1.9458

Max Act: 1.1208. Min Act: -0.0000

Data Index: 273174 (C4 (Web Text))

Max Activating Token Index: 532