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

Dataset: The Pile

Neuron 4479 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.6288. Min Act: -0.0000

Data Index: 160185 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.1168. Min Act: -0.0000

Data Index: 1783425 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.7792. Min Act: -0.0000

Data Index: 486606 (The Pile)

Max Activating Token Index: 36

Text #3

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.5539. Min Act: -0.0000

Data Index: 1464927 (The Pile)

Max Activating Token Index: 896

Text #4

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.2790. Min Act: -0.0000

Data Index: 1137338 (The Pile)

Max Activating Token Index: 545

Text #5

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.4656. Min Act: -0.0000

Data Index: 268285 (The Pile)

Max Activating Token Index: 569

Text #6

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.1108. Min Act: -0.0000

Data Index: 152162 (The Pile)

Max Activating Token Index: 818

Text #7

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.4042. Min Act: -0.0000

Data Index: 1633500 (The Pile)

Max Activating Token Index: 111

Text #8

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.2925. Min Act: -0.0000

Data Index: 1945907 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.2898. Min Act: -0.0000

Data Index: 125275 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.1354. Min Act: -0.0000

Data Index: 1750726 (The Pile)

Max Activating Token Index: 959

Text #11

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.0397. Min Act: -0.0000

Data Index: 716288 (The Pile)

Max Activating Token Index: 42

Text #12

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.5135. Min Act: -0.0000

Data Index: 305119 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.2073. Min Act: -0.0000

Data Index: 935910 (The Pile)

Max Activating Token Index: 394

Text #14

Max Range: 3.7792. Min Range: -3.7792

Max Act: 2.3508. Min Act: -0.0000

Data Index: 1484337 (The Pile)

Max Activating Token Index: 485

Text #15

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.1459. Min Act: -0.0000

Data Index: 826137 (The Pile)

Max Activating Token Index: 420

Text #16

Max Range: 3.7792. Min Range: -3.7792

Max Act: 3.0164. Min Act: -0.0000

Data Index: 1943559 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 3.7792. Min Range: -3.7792

Max Act: 2.9973. Min Act: -0.0000

Data Index: 1578504 (The Pile)

Max Activating Token Index: 1017

Text #18

Max Range: 3.7792. Min Range: -3.7792

Max Act: 2.5264. Min Act: -0.0000

Data Index: 1631784 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 3.7792. Min Range: -3.7792

Max Act: 2.8552. Min Act: -0.0000

Data Index: 1363306 (The Pile)

Max Activating Token Index: 281