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

Dataset: The Pile

Neuron 1347 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: 1.3224. Min Range: -1.3224

Max Act: 1.3224. Min Act: -0.0000

Data Index: 1785898 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2091. Min Act: -0.0000

Data Index: 1736903 (The Pile)

Max Activating Token Index: 353

Text #2

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2419. Min Act: -0.0000

Data Index: 1705995 (The Pile)

Max Activating Token Index: 139

Text #3

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1885. Min Act: -0.0000

Data Index: 1740952 (The Pile)

Max Activating Token Index: 160

Text #4

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2640. Min Act: -0.0000

Data Index: 25408 (The Pile)

Max Activating Token Index: 517

Text #5

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2528. Min Act: -0.0000

Data Index: 497187 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.0862. Min Act: -0.0000

Data Index: 1027695 (The Pile)

Max Activating Token Index: 588

Text #7

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1926109 (The Pile)

Max Activating Token Index: 714

Text #8

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1208. Min Act: -0.0000

Data Index: 709790 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2490. Min Act: -0.0000

Data Index: 1117064 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1593211 (The Pile)

Max Activating Token Index: 526

Text #11

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1570. Min Act: -0.0000

Data Index: 328995 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1908. Min Act: -0.0000

Data Index: 909817 (The Pile)

Max Activating Token Index: 173

Text #13

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1825072 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.0359. Min Act: -0.0000

Data Index: 423549 (The Pile)

Max Activating Token Index: 707

Text #15

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.0902. Min Act: -0.0000

Data Index: 126704 (The Pile)

Max Activating Token Index: 698

Text #16

Max Range: 1.3224. Min Range: -1.3224

Max Act: 0.9882. Min Act: -0.0000

Data Index: 272730 (The Pile)

Max Activating Token Index: 321

Text #17

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.0252. Min Act: -0.0000

Data Index: 418845 (The Pile)

Max Activating Token Index: 845

Text #18

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.0285. Min Act: -0.0000

Data Index: 475495 (The Pile)

Max Activating Token Index: 339

Text #19

Max Range: 1.3224. Min Range: -1.3224

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1302176 (The Pile)

Max Activating Token Index: 97