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

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

Neuron 1883 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.8884. Min Act: -0.0001

Data Index: 1363905 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.7391. Min Act: -0.0001

Data Index: 1625052 (Python Code)

Max Activating Token Index: 836

Text #2

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.5202. Min Act: -0.0000

Data Index: 1462231 (Python Code)

Max Activating Token Index: 284

Text #3

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.4709. Min Act: -0.0001

Data Index: 1571874 (Python Code)

Max Activating Token Index: 621

Text #4

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.3472. Min Act: -0.0001

Data Index: 1492539 (Python Code)

Max Activating Token Index: 924

Text #5

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.3328. Min Act: -0.0001

Data Index: 1466814 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.3222. Min Act: -0.0001

Data Index: 1455667 (Python Code)

Max Activating Token Index: 479

Text #7

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.2626. Min Act: -0.0001

Data Index: 1651468 (Python Code)

Max Activating Token Index: 730

Text #8

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.2435. Min Act: -0.0001

Data Index: 1470412 (Python Code)

Max Activating Token Index: 156

Text #9

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.2010. Min Act: -0.0001

Data Index: 1643085 (Python Code)

Max Activating Token Index: 581

Text #10

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.1242. Min Act: -0.0001

Data Index: 1495017 (Python Code)

Max Activating Token Index: 928

Text #11

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.2909. Min Act: -0.0001

Data Index: 1573717 (Python Code)

Max Activating Token Index: 284

Text #12

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.0837. Min Act: -0.0001

Data Index: 1560891 (Python Code)

Max Activating Token Index: 249

Text #13

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.2073. Min Act: -0.0001

Data Index: 1539739 (Python Code)

Max Activating Token Index: 558

Text #14

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.1674. Min Act: -0.0001

Data Index: 1479282 (Python Code)

Max Activating Token Index: 228

Text #15

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.0763. Min Act: -0.0001

Data Index: 1497104 (Python Code)

Max Activating Token Index: 856

Text #16

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.1285. Min Act: -0.0001

Data Index: 1605892 (Python Code)

Max Activating Token Index: 764

Text #17

Max Range: 1.8884. Min Range: -1.8884

Max Act: 0.8986. Min Act: -0.0001

Data Index: 1430991 (Python Code)

Max Activating Token Index: 736

Text #18

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.1112. Min Act: -0.0001

Data Index: 1544049 (Python Code)

Max Activating Token Index: 159

Text #19

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.1511. Min Act: -0.0001

Data Index: 1525488 (Python Code)

Max Activating Token Index: 698