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

Dataset: The Pile

Neuron 653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1332515 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1392. Min Act: -0.0000

Data Index: 758181 (The Pile)

Max Activating Token Index: 486

Text #2

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1283. Min Act: -0.0000

Data Index: 336993 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1377654 (The Pile)

Max Activating Token Index: 50

Text #4

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1138. Min Act: -0.0000

Data Index: 531102 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1399029 (The Pile)

Max Activating Token Index: 652

Text #6

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1355. Min Act: -0.0000

Data Index: 877260 (The Pile)

Max Activating Token Index: 590

Text #7

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1091803 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1170. Min Act: -0.0000

Data Index: 985066 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1839136 (The Pile)

Max Activating Token Index: 810

Text #10

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1510655 (The Pile)

Max Activating Token Index: 943

Text #11

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.0959. Min Act: -0.0000

Data Index: 813729 (The Pile)

Max Activating Token Index: 942

Text #12

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1791768 (The Pile)

Max Activating Token Index: 883

Text #13

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1362163 (The Pile)

Max Activating Token Index: 596

Text #14

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1219. Min Act: -0.0000

Data Index: 83008 (The Pile)

Max Activating Token Index: 980

Text #15

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1227. Min Act: -0.0000

Data Index: 740066 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1173805 (The Pile)

Max Activating Token Index: 963

Text #17

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1342649 (The Pile)

Max Activating Token Index: 846

Text #18

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1670043 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1940903 (The Pile)

Max Activating Token Index: 990