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

Dataset: The Pile

Neuron 1906 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: 0.1747. Min Range: -0.1747

Max Act: 0.1747. Min Act: -0.0000

Data Index: 356182 (The Pile)

Max Activating Token Index: 902

Text #1

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1379. Min Act: -0.0000

Data Index: 1802072 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1202. Min Act: -0.0000

Data Index: 163616 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1821145 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1260. Min Act: -0.0000

Data Index: 20243 (The Pile)

Max Activating Token Index: 46

Text #5

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1467298 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1199. Min Act: -0.0000

Data Index: 857310 (The Pile)

Max Activating Token Index: 911

Text #7

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1122. Min Act: -0.0000

Data Index: 517324 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1437682 (The Pile)

Max Activating Token Index: 25

Text #9

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1911689 (The Pile)

Max Activating Token Index: 138

Text #10

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1112. Min Act: -0.0000

Data Index: 625144 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1951651 (The Pile)

Max Activating Token Index: 48

Text #12

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1525435 (The Pile)

Max Activating Token Index: 203

Text #13

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1082. Min Act: -0.0000

Data Index: 904177 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1679358 (The Pile)

Max Activating Token Index: 897

Text #15

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1038. Min Act: -0.0000

Data Index: 276827 (The Pile)

Max Activating Token Index: 976

Text #16

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.0934. Min Act: -0.0000

Data Index: 1307939 (The Pile)

Max Activating Token Index: 729

Text #17

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1041. Min Act: -0.0000

Data Index: 1971468 (The Pile)

Max Activating Token Index: 756

Text #18

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1451644 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.0962. Min Act: -0.0000

Data Index: 1636347 (The Pile)

Max Activating Token Index: 152