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

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

Neuron 386 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.3808. Min Act: -0.0000

Data Index: 716996 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.3409. Min Act: -0.0000

Data Index: 26126 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.2878. Min Act: -0.0000

Data Index: 361763 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.2571. Min Act: -0.0000

Data Index: 1190756 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.2932. Min Act: -0.0000

Data Index: 582257 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1804. Min Act: -0.0000

Data Index: 122070 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.2618. Min Act: -0.0000

Data Index: 711722 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.2210. Min Act: -0.0000

Data Index: 427853 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.2246. Min Act: -0.0000

Data Index: 344100 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1556. Min Act: -0.0000

Data Index: 32224 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1308956 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.2187. Min Act: -0.0000

Data Index: 1066307 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1299. Min Act: -0.0000

Data Index: 394831 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1999. Min Act: -0.0000

Data Index: 216663 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1539. Min Act: -0.0000

Data Index: 457327 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1478. Min Act: -0.0000

Data Index: 539609 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1349130 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1403. Min Act: -0.0000

Data Index: 1195013 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1637. Min Act: -0.0000

Data Index: 981441 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1222. Min Act: -0.0000

Data Index: 323592 (C4 (Web Text))

Max Activating Token Index: 668