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

Dataset: The Pile

Neuron 3256 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: 1.5433. Min Range: -1.5433

Max Act: 1.5433. Min Act: -0.0000

Data Index: 726639 (The Pile)

Max Activating Token Index: 482

Text #1

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2900. Min Act: -0.0000

Data Index: 1124185 (The Pile)

Max Activating Token Index: 552

Text #2

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.3981. Min Act: -0.0000

Data Index: 221644 (The Pile)

Max Activating Token Index: 354

Text #3

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.4728. Min Act: -0.0000

Data Index: 905990 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2886. Min Act: -0.0000

Data Index: 70317 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.3430. Min Act: -0.0000

Data Index: 16640 (The Pile)

Max Activating Token Index: 231

Text #6

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2099. Min Act: -0.0000

Data Index: 998002 (The Pile)

Max Activating Token Index: 841

Text #7

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2025. Min Act: -0.0000

Data Index: 1747851 (The Pile)

Max Activating Token Index: 730

Text #8

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.3636. Min Act: -0.0000

Data Index: 762004 (The Pile)

Max Activating Token Index: 895

Text #9

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2148. Min Act: -0.0000

Data Index: 1281039 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2543. Min Act: -0.0000

Data Index: 353669 (The Pile)

Max Activating Token Index: 89

Text #11

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.1110. Min Act: -0.0000

Data Index: 942187 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2811. Min Act: -0.0000

Data Index: 323170 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.1494. Min Act: -0.0000

Data Index: 176742 (The Pile)

Max Activating Token Index: 815

Text #14

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1768478 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.1124. Min Act: -0.0000

Data Index: 1542468 (The Pile)

Max Activating Token Index: 843

Text #16

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1060383 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.1350. Min Act: -0.0000

Data Index: 490711 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.0853. Min Act: -0.0000

Data Index: 1215920 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1532493 (The Pile)

Max Activating Token Index: 271