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

Dataset: The Pile

Neuron 1408 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: 0.3143. Min Range: -0.3143

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1158435 (The Pile)

Max Activating Token Index: 839

Text #1

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1956392 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2920. Min Act: -0.0000

Data Index: 783881 (The Pile)

Max Activating Token Index: 514

Text #3

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1960. Min Act: -0.0000

Data Index: 847918 (The Pile)

Max Activating Token Index: 75

Text #4

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1124029 (The Pile)

Max Activating Token Index: 300

Text #5

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1885753 (The Pile)

Max Activating Token Index: 341

Text #6

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1230836 (The Pile)

Max Activating Token Index: 986

Text #7

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1605533 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1849. Min Act: -0.0000

Data Index: 613628 (The Pile)

Max Activating Token Index: 942

Text #9

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1342382 (The Pile)

Max Activating Token Index: 951

Text #10

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1473424 (The Pile)

Max Activating Token Index: 565

Text #11

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1722. Min Act: -0.0000

Data Index: 171883 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1657. Min Act: -0.0000

Data Index: 591095 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1163782 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1974134 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1073576 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1945119 (The Pile)

Max Activating Token Index: 733

Text #17

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1704. Min Act: -0.0000

Data Index: 924964 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1418. Min Act: -0.0000

Data Index: 686466 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1973. Min Act: -0.0000

Data Index: 301012 (The Pile)

Max Activating Token Index: 142