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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4663 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.7601. Min Act: -0.0000

Data Index: 93782 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.6174. Min Act: -0.0000

Data Index: 1277588 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.3274. Min Act: -0.0000

Data Index: 1124322 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.4332. Min Act: -0.0000

Data Index: 682469 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.4307. Min Act: -0.0000

Data Index: 1228337 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.2699. Min Act: -0.0000

Data Index: 358410 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.1831. Min Act: -0.0000

Data Index: 379577 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.2238. Min Act: -0.0000

Data Index: 452519 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.3430. Min Act: -0.0000

Data Index: 263428 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.1894. Min Act: -0.0000

Data Index: 332042 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.2753. Min Act: -0.0000

Data Index: 1079568 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.2376. Min Act: -0.0000

Data Index: 525168 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.1115. Min Act: -0.0000

Data Index: 1282420 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.0865. Min Act: -0.0000

Data Index: 1050780 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.0869. Min Act: -0.0000

Data Index: 250768 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.1742. Min Act: -0.0000

Data Index: 1267825 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.0468. Min Act: -0.0000

Data Index: 1322251 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.1471. Min Act: -0.0000

Data Index: 229493 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.1439. Min Act: -0.0000

Data Index: 1212545 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 2.7601. Min Range: -2.7601

Max Act: 2.1417. Min Act: -0.0000

Data Index: 1131357 (C4 (Web Text))

Max Activating Token Index: 978