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

Dataset: The Pile

Neuron 0 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: 0.2049. Min Range: -0.2049

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1682599 (The Pile)

Max Activating Token Index: 766

Text #1

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1308383 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1708. Min Act: -0.0000

Data Index: 626054 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1879. Min Act: -0.0000

Data Index: 376249 (The Pile)

Max Activating Token Index: 522

Text #4

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1773. Min Act: -0.0000

Data Index: 660541 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1999420 (The Pile)

Max Activating Token Index: 721

Text #6

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1463. Min Act: -0.0000

Data Index: 881729 (The Pile)

Max Activating Token Index: 990

Text #7

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1620. Min Act: -0.0000

Data Index: 81546 (The Pile)

Max Activating Token Index: 864

Text #8

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1105184 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1824363 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1530. Min Act: -0.0000

Data Index: 1520698 (The Pile)

Max Activating Token Index: 741

Text #11

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1331127 (The Pile)

Max Activating Token Index: 427

Text #12

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1237804 (The Pile)

Max Activating Token Index: 356

Text #13

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1590. Min Act: -0.0000

Data Index: 867287 (The Pile)

Max Activating Token Index: 143

Text #14

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1140468 (The Pile)

Max Activating Token Index: 237

Text #15

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1415. Min Act: -0.0000

Data Index: 189425 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1442. Min Act: -0.0000

Data Index: 358835 (The Pile)

Max Activating Token Index: 516

Text #17

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1242139 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1486. Min Act: -0.0000

Data Index: 194700 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1423. Min Act: -0.0000

Data Index: 42358 (The Pile)

Max Activating Token Index: 787