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

Dataset: The Pile

Neuron 2206 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: 1.5658. Min Range: -1.5658

Max Act: 1.4525. Min Act: -0.0000

Data Index: 570293 (The Pile)

Max Activating Token Index: 544

Text #1

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.5658. Min Act: -0.0000

Data Index: 471250 (The Pile)

Max Activating Token Index: 302

Text #2

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.5116. Min Act: -0.0000

Data Index: 363673 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.5117. Min Act: -0.0000

Data Index: 130810 (The Pile)

Max Activating Token Index: 94

Text #4

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.2075. Min Act: -0.0000

Data Index: 933731 (The Pile)

Max Activating Token Index: 746

Text #5

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4553. Min Act: -0.0000

Data Index: 1632593 (The Pile)

Max Activating Token Index: 95

Text #6

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.2928. Min Act: -0.0000

Data Index: 825263 (The Pile)

Max Activating Token Index: 26

Text #7

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1499337 (The Pile)

Max Activating Token Index: 433

Text #8

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.2057. Min Act: -0.0000

Data Index: 102848 (The Pile)

Max Activating Token Index: 463

Text #9

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4359. Min Act: -0.0000

Data Index: 1699881 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.2734. Min Act: -0.0000

Data Index: 1606804 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.2581. Min Act: -0.0000

Data Index: 849711 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.2459. Min Act: -0.0000

Data Index: 1050306 (The Pile)

Max Activating Token Index: 856

Text #13

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.3105. Min Act: -0.0000

Data Index: 1675725 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.2301. Min Act: -0.0000

Data Index: 919643 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.1799. Min Act: -0.0000

Data Index: 856470 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1174067 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.1430. Min Act: -0.0000

Data Index: 1401265 (The Pile)

Max Activating Token Index: 5

Text #18

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.1915. Min Act: -0.0000

Data Index: 1501259 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1841563 (The Pile)

Max Activating Token Index: 1000