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

Dataset: The Pile

Neuron 1205 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: 0.4737. Min Range: -0.4737

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1445482 (The Pile)

Max Activating Token Index: 148

Text #1

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1351293 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1554573 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.4370. Min Act: -0.0000

Data Index: 134780 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1025219 (The Pile)

Max Activating Token Index: 99

Text #5

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.4063. Min Act: -0.0000

Data Index: 512613 (The Pile)

Max Activating Token Index: 274

Text #6

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.4233. Min Act: -0.0000

Data Index: 395748 (The Pile)

Max Activating Token Index: 377

Text #7

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1620445 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1297160 (The Pile)

Max Activating Token Index: 599

Text #9

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3991. Min Act: -0.0000

Data Index: 320540 (The Pile)

Max Activating Token Index: 314

Text #10

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1084055 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1306886 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3812. Min Act: -0.0000

Data Index: 669043 (The Pile)

Max Activating Token Index: 70

Text #13

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1430217 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3739. Min Act: -0.0000

Data Index: 67429 (The Pile)

Max Activating Token Index: 199

Text #15

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1595194 (The Pile)

Max Activating Token Index: 337

Text #16

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1166964 (The Pile)

Max Activating Token Index: 543

Text #17

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1369458 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3552. Min Act: -0.0000

Data Index: 237010 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 0.4737. Min Range: -0.4737

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1008490 (The Pile)

Max Activating Token Index: 455