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

Dataset: The Pile

Neuron 358 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: 0.1478. Min Range: -0.1478

Max Act: 0.1478. Min Act: -0.0000

Data Index: 1606090 (The Pile)

Max Activating Token Index: 401

Text #1

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1101850 (The Pile)

Max Activating Token Index: 408

Text #2

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1313210 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1246. Min Act: -0.0000

Data Index: 312708 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1788014 (The Pile)

Max Activating Token Index: 583

Text #5

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1052. Min Act: -0.0000

Data Index: 874525 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1199. Min Act: -0.0000

Data Index: 858810 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1287. Min Act: -0.0000

Data Index: 665971 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1138019 (The Pile)

Max Activating Token Index: 176

Text #9

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1110. Min Act: -0.0000

Data Index: 1932422 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1124. Min Act: -0.0000

Data Index: 444723 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1023. Min Act: -0.0000

Data Index: 718615 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1292938 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0977. Min Act: -0.0000

Data Index: 651737 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0961. Min Act: -0.0000

Data Index: 722094 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1651542 (The Pile)

Max Activating Token Index: 806

Text #16

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1018. Min Act: -0.0000

Data Index: 504478 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1672974 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1421902 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1007. Min Act: -0.0000

Data Index: 414310 (The Pile)

Max Activating Token Index: 428