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

Dataset: The Pile

Neuron 4642 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: 1.3556. Min Range: -1.3556

Max Act: 1.3556. Min Act: -0.0000

Data Index: 372656 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1626. Min Act: -0.0000

Data Index: 1397124 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.3136. Min Act: -0.0000

Data Index: 1019910 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2885. Min Act: -0.0000

Data Index: 1822524 (The Pile)

Max Activating Token Index: 171

Text #4

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1364920 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1900. Min Act: -0.0000

Data Index: 517537 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1439. Min Act: -0.0000

Data Index: 1777092 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1187594 (The Pile)

Max Activating Token Index: 592

Text #8

Max Range: 1.3556. Min Range: -1.3556

Max Act: 0.8363. Min Act: -0.0000

Data Index: 417789 (The Pile)

Max Activating Token Index: 922

Text #9

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1894389 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1415636 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1842. Min Act: -0.0000

Data Index: 531206 (The Pile)

Max Activating Token Index: 686

Text #12

Max Range: 1.3556. Min Range: -1.3556

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1457408 (The Pile)

Max Activating Token Index: 292

Text #13

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1302. Min Act: -0.0000

Data Index: 507846 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1297998 (The Pile)

Max Activating Token Index: 282

Text #15

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0795. Min Act: -0.0000

Data Index: 1795939 (The Pile)

Max Activating Token Index: 203

Text #16

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0087. Min Act: -0.0000

Data Index: 168696 (The Pile)

Max Activating Token Index: 956

Text #17

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0302. Min Act: -0.0000

Data Index: 1123327 (The Pile)

Max Activating Token Index: 35

Text #18

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1046104 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0570. Min Act: -0.0000

Data Index: 996063 (The Pile)

Max Activating Token Index: 100