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

Dataset: The Pile

Neuron 736 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: 3.1617. Min Range: -3.1617

Max Act: 2.9435. Min Act: -0.0000

Data Index: 147193 (The Pile)

Max Activating Token Index: 262

Text #1

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0727. Min Act: -0.0000

Data Index: 634868 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.9147. Min Act: -0.0000

Data Index: 1804580 (The Pile)

Max Activating Token Index: 608

Text #3

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.1617. Min Act: -0.0000

Data Index: 483407 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.1106. Min Act: -0.0000

Data Index: 1657071 (The Pile)

Max Activating Token Index: 947

Text #5

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.9290. Min Act: -0.0000

Data Index: 1069242 (The Pile)

Max Activating Token Index: 349

Text #6

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.9030. Min Act: -0.0000

Data Index: 1093067 (The Pile)

Max Activating Token Index: 749

Text #7

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.8714. Min Act: -0.0000

Data Index: 1512238 (The Pile)

Max Activating Token Index: 873

Text #8

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.0056. Min Act: -0.0000

Data Index: 277235 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.8675. Min Act: -0.0000

Data Index: 537310 (The Pile)

Max Activating Token Index: 40

Text #10

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.9954. Min Act: -0.0000

Data Index: 672343 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.6984. Min Act: -0.0000

Data Index: 250741 (The Pile)

Max Activating Token Index: 790

Text #12

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.5384. Min Act: -0.0000

Data Index: 298204 (The Pile)

Max Activating Token Index: 890

Text #13

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.6632. Min Act: -0.0000

Data Index: 1448638 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.7912. Min Act: -0.0000

Data Index: 1738106 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.9364. Min Act: -0.0000

Data Index: 58316 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.7452. Min Act: -0.0000

Data Index: 1954183 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.4970. Min Act: -0.0000

Data Index: 1176920 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.7588. Min Act: -0.0000

Data Index: 1875091 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.7312. Min Act: -0.0000

Data Index: 646410 (The Pile)

Max Activating Token Index: 665