Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 521 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1950675 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1825. Min Act: -0.0000

Data Index: 335045 (The Pile)

Max Activating Token Index: 634

Text #2

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1760. Min Act: -0.0000

Data Index: 508020 (The Pile)

Max Activating Token Index: 289

Text #3

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1128515 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1668. Min Act: -0.0000

Data Index: 508900 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1522. Min Act: -0.0000

Data Index: 978420 (The Pile)

Max Activating Token Index: 396

Text #6

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1083645 (The Pile)

Max Activating Token Index: 619

Text #7

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1496. Min Act: -0.0000

Data Index: 511237 (The Pile)

Max Activating Token Index: 334

Text #8

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1442. Min Act: -0.0000

Data Index: 868324 (The Pile)

Max Activating Token Index: 89

Text #9

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1554641 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1272. Min Act: -0.0000

Data Index: 353855 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1368. Min Act: -0.0000

Data Index: 327690 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1422. Min Act: -0.0000

Data Index: 702034 (The Pile)

Max Activating Token Index: 756

Text #13

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1917528 (The Pile)

Max Activating Token Index: 373

Text #14

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1450966 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1250. Min Act: -0.0000

Data Index: 872788 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1866744 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1294. Min Act: -0.0000

Data Index: 209187 (The Pile)

Max Activating Token Index: 313

Text #18

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1035857 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1329. Min Act: -0.0000

Data Index: 207018 (The Pile)

Max Activating Token Index: 312