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

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

Neuron 1766 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3741. Min Act: -0.0000

Data Index: 555844 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2984. Min Act: -0.0000

Data Index: 271947 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2739. Min Act: -0.0000

Data Index: 314836 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1222541 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2463. Min Act: -0.0000

Data Index: 857209 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1144599 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2165. Min Act: -0.0000

Data Index: 670007 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1295235 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1106381 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1267275 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.1975. Min Act: -0.0000

Data Index: 835134 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.1971. Min Act: -0.0000

Data Index: 562663 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.1915. Min Act: -0.0000

Data Index: 516099 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1286958 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.1966. Min Act: -0.0000

Data Index: 813089 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.1800. Min Act: -0.0000

Data Index: 678254 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.1796. Min Act: -0.0000

Data Index: 943889 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.1790. Min Act: -0.0000

Data Index: 987431 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1214993 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.1802. Min Act: -0.0000

Data Index: 486727 (C4 (Web Text))

Max Activating Token Index: 127