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

Dataset: The Pile

Neuron 988 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: 1.6375. Min Range: -1.6375

Max Act: 1.6375. Min Act: -0.0000

Data Index: 1243917 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1975631 (The Pile)

Max Activating Token Index: 497

Text #2

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.2032. Min Act: -0.0000

Data Index: 1011735 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.2051. Min Act: -0.0000

Data Index: 1724199 (The Pile)

Max Activating Token Index: 457

Text #4

Max Range: 1.6375. Min Range: -1.6375

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1711670 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.1020. Min Act: -0.0000

Data Index: 51952 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.1635. Min Act: -0.0000

Data Index: 494010 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.1418. Min Act: -0.0000

Data Index: 1341392 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1271095 (The Pile)

Max Activating Token Index: 891

Text #9

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.1217. Min Act: -0.0000

Data Index: 966920 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.0879. Min Act: -0.0000

Data Index: 227518 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.0851. Min Act: -0.0000

Data Index: 489272 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1188493 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 1.6375. Min Range: -1.6375

Max Act: 0.9993. Min Act: -0.0000

Data Index: 526088 (The Pile)

Max Activating Token Index: 284

Text #14

Max Range: 1.6375. Min Range: -1.6375

Max Act: 0.9485. Min Act: -0.0000

Data Index: 558535 (The Pile)

Max Activating Token Index: 802

Text #15

Max Range: 1.6375. Min Range: -1.6375

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1181656 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.0662. Min Act: -0.0000

Data Index: 381807 (The Pile)

Max Activating Token Index: 472

Text #17

Max Range: 1.6375. Min Range: -1.6375

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1570171 (The Pile)

Max Activating Token Index: 774

Text #18

Max Range: 1.6375. Min Range: -1.6375

Max Act: 0.9220. Min Act: -0.0000

Data Index: 383191 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 1.6375. Min Range: -1.6375

Max Act: 0.9039. Min Act: -0.0000

Data Index: 796623 (The Pile)

Max Activating Token Index: 218