Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2973 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.3900. Min Act: -0.0000

Data Index: 1591219 (The Pile)

Max Activating Token Index: 843

Text #1

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.1616. Min Act: -0.0000

Data Index: 1159504 (The Pile)

Max Activating Token Index: 949

Text #2

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.2171. Min Act: -0.0000

Data Index: 1981420 (The Pile)

Max Activating Token Index: 36

Text #3

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1376025 (The Pile)

Max Activating Token Index: 1021

Text #4

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.1864. Min Act: -0.0000

Data Index: 1862395 (The Pile)

Max Activating Token Index: 508

Text #5

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.1641. Min Act: 0.0000

Data Index: 188575 (The Pile)

Max Activating Token Index: 349

Text #6

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.1322. Min Act: -0.0000

Data Index: 997050 (The Pile)

Max Activating Token Index: 381

Text #7

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.1140. Min Act: -0.0000

Data Index: 19937 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0210. Min Act: 0.0000

Data Index: 212660 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.1137. Min Act: 0.0000

Data Index: 971214 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0438. Min Act: -0.0000

Data Index: 1795844 (The Pile)

Max Activating Token Index: 860

Text #11

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1708302 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.1234. Min Act: -0.0000

Data Index: 1534468 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0699. Min Act: -0.0000

Data Index: 1242745 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1592004 (The Pile)

Max Activating Token Index: 399

Text #15

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0246. Min Act: -0.0000

Data Index: 181778 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.1093. Min Act: -0.0000

Data Index: 138638 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0064. Min Act: -0.0000

Data Index: 210683 (The Pile)

Max Activating Token Index: 621

Text #18

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0596. Min Act: -0.0000

Data Index: 514196 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1219104 (The Pile)

Max Activating Token Index: 897