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

Dataset: The Pile

Neuron 2536 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1966524 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1657. Min Act: -0.0000

Data Index: 405108 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1836. Min Act: -0.0001

Data Index: 778830 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1430412 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1664. Min Act: -0.0000

Data Index: 855480 (The Pile)

Max Activating Token Index: 335

Text #5

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1517. Min Act: -0.0001

Data Index: 714265 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1782. Min Act: -0.0000

Data Index: 529967 (The Pile)

Max Activating Token Index: 79

Text #7

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1538. Min Act: -0.0000

Data Index: 532733 (The Pile)

Max Activating Token Index: 102

Text #8

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1547818 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1436. Min Act: -0.0000

Data Index: 679260 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1465. Min Act: -0.0000

Data Index: 437327 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1670308 (The Pile)

Max Activating Token Index: 814

Text #12

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1552003 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1956526 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1465. Min Act: -0.0000

Data Index: 972283 (The Pile)

Max Activating Token Index: 707

Text #15

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1037376 (The Pile)

Max Activating Token Index: 294

Text #16

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1956129 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1449. Min Act: -0.0000

Data Index: 598781 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1594. Min Act: -0.0000

Data Index: 650302 (The Pile)

Max Activating Token Index: 861

Text #19

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1355093 (The Pile)

Max Activating Token Index: 242