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

Dataset: The Pile

Neuron 72 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1149. Min Range: -1.1149

Max Act: 1.1149. Min Act: -0.0000

Data Index: 1774740 (The Pile)

Max Activating Token Index: 732

Text #1

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.7829. Min Act: -0.0000

Data Index: 576744 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1726617 (The Pile)

Max Activating Token Index: 662

Text #3

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1472524 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.9284. Min Act: -0.0000

Data Index: 1075058 (The Pile)

Max Activating Token Index: 770

Text #5

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.8670. Min Act: -0.0000

Data Index: 1550705 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.8082. Min Act: -0.0000

Data Index: 569479 (The Pile)

Max Activating Token Index: 600

Text #7

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.7394. Min Act: -0.0000

Data Index: 573148 (The Pile)

Max Activating Token Index: 204

Text #8

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.7873. Min Act: -0.0000

Data Index: 773749 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1922115 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1252380 (The Pile)

Max Activating Token Index: 601

Text #11

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.7723. Min Act: -0.0000

Data Index: 999908 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1271087 (The Pile)

Max Activating Token Index: 346

Text #13

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1001799 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1850999 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.7092. Min Act: -0.0000

Data Index: 1042548 (The Pile)

Max Activating Token Index: 482

Text #16

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.7020. Min Act: -0.0000

Data Index: 741 (The Pile)

Max Activating Token Index: 605

Text #17

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.7061. Min Act: -0.0000

Data Index: 427619 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.8087. Min Act: -0.0000

Data Index: 494053 (The Pile)

Max Activating Token Index: 896

Text #19

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.7839. Min Act: -0.0001

Data Index: 1396051 (The Pile)

Max Activating Token Index: 877