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

Dataset: The Pile

Neuron 760 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1525. Min Range: -5.1525

Max Act: 5.1525. Min Act: -0.0000

Data Index: 148685 (The Pile)

Max Activating Token Index: 377

Text #1

Max Range: 5.1525. Min Range: -5.1525

Max Act: 4.6010. Min Act: -0.0000

Data Index: 1657264 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 5.1525. Min Range: -5.1525

Max Act: 4.6604. Min Act: -0.0000

Data Index: 1006881 (The Pile)

Max Activating Token Index: 891

Text #3

Max Range: 5.1525. Min Range: -5.1525

Max Act: 4.6921. Min Act: -0.0000

Data Index: 1598939 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 5.1525. Min Range: -5.1525

Max Act: 4.2966. Min Act: -0.0000

Data Index: 1139266 (The Pile)

Max Activating Token Index: 141

Text #5

Max Range: 5.1525. Min Range: -5.1525

Max Act: 4.0961. Min Act: -0.0000

Data Index: 1629404 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 5.1525. Min Range: -5.1525

Max Act: 4.2826. Min Act: -0.0000

Data Index: 1227339 (The Pile)

Max Activating Token Index: 626

Text #7

Max Range: 5.1525. Min Range: -5.1525

Max Act: 4.0689. Min Act: -0.0000

Data Index: 1598444 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 5.1525. Min Range: -5.1525

Max Act: 4.2241. Min Act: -0.0000

Data Index: 1737102 (The Pile)

Max Activating Token Index: 392

Text #9

Max Range: 5.1525. Min Range: -5.1525

Max Act: 4.0601. Min Act: -0.0000

Data Index: 304721 (The Pile)

Max Activating Token Index: 436

Text #10

Max Range: 5.1525. Min Range: -5.1525

Max Act: 4.2294. Min Act: -0.0000

Data Index: 1344614 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 5.1525. Min Range: -5.1525

Max Act: 3.8538. Min Act: -0.0000

Data Index: 105964 (The Pile)

Max Activating Token Index: 490

Text #12

Max Range: 5.1525. Min Range: -5.1525

Max Act: 4.3234. Min Act: -0.0000

Data Index: 661895 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 5.1525. Min Range: -5.1525

Max Act: 4.0953. Min Act: -0.0000

Data Index: 980092 (The Pile)

Max Activating Token Index: 165

Text #14

Max Range: 5.1525. Min Range: -5.1525

Max Act: 4.1494. Min Act: -0.0000

Data Index: 299811 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 5.1525. Min Range: -5.1525

Max Act: 3.9352. Min Act: -0.0000

Data Index: 1630983 (The Pile)

Max Activating Token Index: 249

Text #16

Max Range: 5.1525. Min Range: -5.1525

Max Act: 3.8774. Min Act: -0.0000

Data Index: 1659911 (The Pile)

Max Activating Token Index: 264

Text #17

Max Range: 5.1525. Min Range: -5.1525

Max Act: 3.7152. Min Act: -0.0000

Data Index: 339423 (The Pile)

Max Activating Token Index: 848

Text #18

Max Range: 5.1525. Min Range: -5.1525

Max Act: 3.8364. Min Act: -0.0000

Data Index: 248846 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 5.1525. Min Range: -5.1525

Max Act: 3.6964. Min Act: -0.0000

Data Index: 493758 (The Pile)

Max Activating Token Index: 760