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

Dataset: The Pile

Neuron 4607 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: 3.1126. Min Range: -3.1126

Max Act: 3.1126. Min Act: -0.0000

Data Index: 308080 (The Pile)

Max Activating Token Index: 509

Text #1

Max Range: 3.1126. Min Range: -3.1126

Max Act: 3.0833. Min Act: -0.0000

Data Index: 1632016 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.9461. Min Act: -0.0000

Data Index: 809638 (The Pile)

Max Activating Token Index: 237

Text #3

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.6786. Min Act: -0.0000

Data Index: 134767 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.6584. Min Act: -0.0000

Data Index: 1713729 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.6442. Min Act: -0.0000

Data Index: 116483 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.5043. Min Act: -0.0000

Data Index: 121652 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.5938. Min Act: -0.0000

Data Index: 1015806 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.4755. Min Act: -0.0000

Data Index: 1528509 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.5081. Min Act: -0.0000

Data Index: 126652 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.3625. Min Act: -0.0000

Data Index: 273075 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.4443. Min Act: -0.0000

Data Index: 1507476 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.4430. Min Act: -0.0000

Data Index: 1239552 (The Pile)

Max Activating Token Index: 162

Text #13

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.6389. Min Act: -0.0000

Data Index: 486324 (The Pile)

Max Activating Token Index: 374

Text #14

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.2641. Min Act: -0.0000

Data Index: 1823316 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.5043. Min Act: -0.0000

Data Index: 639562 (The Pile)

Max Activating Token Index: 21

Text #16

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.3729. Min Act: -0.0000

Data Index: 453920 (The Pile)

Max Activating Token Index: 346

Text #17

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.1505. Min Act: -0.0000

Data Index: 140664 (The Pile)

Max Activating Token Index: 211

Text #18

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.4528. Min Act: -0.0000

Data Index: 1637705 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 3.1126. Min Range: -3.1126

Max Act: 2.0208. Min Act: -0.0000

Data Index: 1053249 (The Pile)

Max Activating Token Index: 786