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

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

Neuron 2760 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: 0.2189. Min Range: -0.2189

Max Act: 0.2189. Min Act: 0.0000

Data Index: 317401 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.2179. Min Act: 0.0001

Data Index: 111262 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1989. Min Act: -0.0000

Data Index: 851859 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1933. Min Act: 0.0000

Data Index: 440077 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1753. Min Act: 0.0001

Data Index: 93802 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1775. Min Act: 0.0000

Data Index: 754460 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1904. Min Act: 0.0001

Data Index: 1063402 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1860. Min Act: 0.0001

Data Index: 753158 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1602. Min Act: -0.0000

Data Index: 610657 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1670. Min Act: -0.0000

Data Index: 907186 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1634. Min Act: 0.0001

Data Index: 1245276 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1706. Min Act: -0.0001

Data Index: 235348 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1227467 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1174596 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1317758 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1565. Min Act: 0.0001

Data Index: 1006057 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1516. Min Act: 0.0000

Data Index: 504639 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1343. Min Act: 0.0000

Data Index: 430771 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1526. Min Act: -0.0000

Data Index: 874466 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1498. Min Act: 0.0000

Data Index: 750817 (C4 (Web Text))

Max Activating Token Index: 760