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

Dataset: The Pile

Neuron 1104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.6435. Min Act: -0.0000

Data Index: 767830 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1429528 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1778558 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1124103 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5488. Min Act: -0.0000

Data Index: 538878 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1336169 (The Pile)

Max Activating Token Index: 881

Text #6

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1531398 (The Pile)

Max Activating Token Index: 526

Text #7

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1851895 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5118. Min Act: -0.0000

Data Index: 244910 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5513. Min Act: -0.0000

Data Index: 774197 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.4955. Min Act: -0.0000

Data Index: 364575 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5245. Min Act: -0.0000

Data Index: 944545 (The Pile)

Max Activating Token Index: 363

Text #12

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1144283 (The Pile)

Max Activating Token Index: 948

Text #13

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5061. Min Act: -0.0000

Data Index: 30701 (The Pile)

Max Activating Token Index: 81

Text #14

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1187090 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1655154 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1324139 (The Pile)

Max Activating Token Index: 805

Text #17

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1538271 (The Pile)

Max Activating Token Index: 382

Text #18

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1609065 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1324922 (The Pile)

Max Activating Token Index: 888