Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2597 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2548. Min Act: -0.0000

Data Index: 793510 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1930175 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1064002 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1882. Min Act: -0.0000

Data Index: 548197 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1633124 (The Pile)

Max Activating Token Index: 518

Text #5

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1970. Min Act: 0.0000

Data Index: 1862125 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1901. Min Act: 0.0000

Data Index: 541910 (The Pile)

Max Activating Token Index: 394

Text #7

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1999788 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1520513 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1345411 (The Pile)

Max Activating Token Index: 443

Text #10

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1669. Min Act: -0.0000

Data Index: 717346 (The Pile)

Max Activating Token Index: 78

Text #11

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1677. Min Act: -0.0000

Data Index: 692900 (The Pile)

Max Activating Token Index: 269

Text #12

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1691. Min Act: -0.0000

Data Index: 948382 (The Pile)

Max Activating Token Index: 276

Text #13

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1717. Min Act: -0.0000

Data Index: 253347 (The Pile)

Max Activating Token Index: 532

Text #14

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1781753 (The Pile)

Max Activating Token Index: 991

Text #15

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1619. Min Act: -0.0000

Data Index: 1522136 (The Pile)

Max Activating Token Index: 175

Text #16

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1594. Min Act: 0.0000

Data Index: 313042 (The Pile)

Max Activating Token Index: 288

Text #17

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1530. Min Act: -0.0000

Data Index: 567024 (The Pile)

Max Activating Token Index: 141

Text #18

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1209768 (The Pile)

Max Activating Token Index: 128

Text #19

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1970081 (The Pile)

Max Activating Token Index: 168