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

Dataset: The Pile

Neuron 2117 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2846. Min Range: -1.2846

Max Act: 1.2846. Min Act: -0.0000

Data Index: 1747820 (The Pile)

Max Activating Token Index: 623

Text #1

Max Range: 1.2846. Min Range: -1.2846

Max Act: 1.1024. Min Act: -0.0000

Data Index: 425913 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 1.2846. Min Range: -1.2846

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1716135 (The Pile)

Max Activating Token Index: 434

Text #3

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1567020 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1498342 (The Pile)

Max Activating Token Index: 827

Text #5

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.7465. Min Act: -0.0000

Data Index: 172768 (The Pile)

Max Activating Token Index: 624

Text #6

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.7142. Min Act: -0.0000

Data Index: 398846 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.6384. Min Act: -0.0000

Data Index: 8397 (The Pile)

Max Activating Token Index: 863

Text #8

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.6401. Min Act: -0.0000

Data Index: 335596 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1845347 (The Pile)

Max Activating Token Index: 409

Text #10

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1046943 (The Pile)

Max Activating Token Index: 1001

Text #11

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.6447. Min Act: 0.0000

Data Index: 1562714 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.6092. Min Act: -0.0000

Data Index: 851731 (The Pile)

Max Activating Token Index: 624

Text #13

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.6007. Min Act: -0.0000

Data Index: 567009 (The Pile)

Max Activating Token Index: 122

Text #14

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.5410. Min Act: -0.0000

Data Index: 698231 (The Pile)

Max Activating Token Index: 944

Text #15

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1326470 (The Pile)

Max Activating Token Index: 864

Text #16

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1559900 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.6001. Min Act: -0.0000

Data Index: 524724 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.5778. Min Act: -0.0000

Data Index: 777077 (The Pile)

Max Activating Token Index: 853

Text #19

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.6017. Min Act: -0.0000

Data Index: 341460 (The Pile)

Max Activating Token Index: 805