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

Dataset: The Pile

Neuron 3290 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.3805. Min Act: -0.0000

Data Index: 418704 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.3087. Min Act: -0.0000

Data Index: 1134869 (The Pile)

Max Activating Token Index: 886

Text #2

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.4116. Min Act: -0.0000

Data Index: 203615 (The Pile)

Max Activating Token Index: 477

Text #3

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.3083. Min Act: -0.0000

Data Index: 1792866 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.2425. Min Act: -0.0000

Data Index: 205345 (The Pile)

Max Activating Token Index: 788

Text #5

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1646117 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.2483. Min Act: -0.0000

Data Index: 481095 (The Pile)

Max Activating Token Index: 331

Text #7

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.2622. Min Act: -0.0000

Data Index: 721581 (The Pile)

Max Activating Token Index: 737

Text #8

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.3227. Min Act: -0.0000

Data Index: 1169622 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.1868. Min Act: -0.0000

Data Index: 13444 (The Pile)

Max Activating Token Index: 755

Text #10

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1177606 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.1301. Min Act: -0.0000

Data Index: 1355029 (The Pile)

Max Activating Token Index: 992

Text #12

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.1574. Min Act: -0.0000

Data Index: 1907914 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.1543. Min Act: -0.0000

Data Index: 1876639 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.1263. Min Act: -0.0000

Data Index: 1915671 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1361511 (The Pile)

Max Activating Token Index: 68

Text #16

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.0838. Min Act: -0.0000

Data Index: 1723740 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.0922. Min Act: -0.0000

Data Index: 262084 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1610601 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 1.4116. Min Range: -1.4116

Max Act: 1.0594. Min Act: -0.0000

Data Index: 236692 (The Pile)

Max Activating Token Index: 672