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

Dataset: The Pile

Neuron 71 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: 1.4237. Min Range: -1.4237

Max Act: 1.4237. Min Act: -0.0000

Data Index: 121204 (The Pile)

Max Activating Token Index: 518

Text #1

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1760101 (The Pile)

Max Activating Token Index: 804

Text #2

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.2539. Min Act: -0.0000

Data Index: 1776502 (The Pile)

Max Activating Token Index: 985

Text #3

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.2152. Min Act: -0.0000

Data Index: 1534787 (The Pile)

Max Activating Token Index: 561

Text #4

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.2530. Min Act: -0.0000

Data Index: 875671 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.2501. Min Act: -0.0000

Data Index: 1455172 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.2529. Min Act: -0.0000

Data Index: 114788 (The Pile)

Max Activating Token Index: 194

Text #7

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1745. Min Act: -0.0000

Data Index: 216263 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1081. Min Act: -0.0000

Data Index: 287913 (The Pile)

Max Activating Token Index: 947

Text #9

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1347. Min Act: -0.0000

Data Index: 933472 (The Pile)

Max Activating Token Index: 626

Text #10

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1293. Min Act: -0.0000

Data Index: 190705 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1444. Min Act: -0.0000

Data Index: 1309650 (The Pile)

Max Activating Token Index: 195

Text #12

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.0703. Min Act: -0.0000

Data Index: 1704633 (The Pile)

Max Activating Token Index: 574

Text #13

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.0635. Min Act: -0.0000

Data Index: 305775 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.0244. Min Act: -0.0000

Data Index: 150634 (The Pile)

Max Activating Token Index: 944

Text #15

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1324. Min Act: -0.0000

Data Index: 834509 (The Pile)

Max Activating Token Index: 960

Text #16

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.0310. Min Act: -0.0000

Data Index: 944298 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.0522. Min Act: -0.0000

Data Index: 685376 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1048. Min Act: -0.0000

Data Index: 1876073 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1834928 (The Pile)

Max Activating Token Index: 309