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

Dataset: The Pile

Neuron 2485 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: 0.7336. Min Range: -0.7336

Max Act: 0.7336. Min Act: -0.0000

Data Index: 966970 (The Pile)

Max Activating Token Index: 141

Text #1

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1869106 (The Pile)

Max Activating Token Index: 749

Text #2

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1602157 (The Pile)

Max Activating Token Index: 308

Text #3

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5883. Min Act: -0.0000

Data Index: 602461 (The Pile)

Max Activating Token Index: 654

Text #4

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1345789 (The Pile)

Max Activating Token Index: 708

Text #5

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1466221 (The Pile)

Max Activating Token Index: 44

Text #6

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4909. Min Act: -0.0000

Data Index: 121421 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5466. Min Act: -0.0000

Data Index: 249340 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4838. Min Act: -0.0000

Data Index: 877973 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4747. Min Act: -0.0000

Data Index: 35167 (The Pile)

Max Activating Token Index: 350

Text #10

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4958. Min Act: -0.0000

Data Index: 105501 (The Pile)

Max Activating Token Index: 359

Text #11

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4772. Min Act: -0.0000

Data Index: 828328 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1337836 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1097896 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1689231 (The Pile)

Max Activating Token Index: 122

Text #15

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1779876 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5014. Min Act: -0.0000

Data Index: 929450 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1910835 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1763295 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4389. Min Act: -0.0000

Data Index: 722388 (The Pile)

Max Activating Token Index: 43