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

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

Neuron 2631 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2792. Min Act: -0.0000

Data Index: 709252 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2850. Min Act: -0.0000

Data Index: 923524 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2567. Min Act: -0.0000

Data Index: 410870 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2837. Min Act: -0.0000

Data Index: 793158 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2652. Min Act: -0.0001

Data Index: 189425 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2753. Min Act: -0.0000

Data Index: 191514 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2558. Min Act: -0.0000

Data Index: 431476 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2480. Min Act: -0.0000

Data Index: 768273 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2307. Min Act: -0.0001

Data Index: 224975 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2283. Min Act: -0.0000

Data Index: 295124 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2336. Min Act: -0.0000

Data Index: 445077 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1017685 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2336. Min Act: -0.0001

Data Index: 1510412 (Python Code)

Max Activating Token Index: 266

Text #13

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2390. Min Act: -0.0000

Data Index: 978420 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2285. Min Act: -0.0001

Data Index: 1360411 (Python Code)

Max Activating Token Index: 1018

Text #15

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2491. Min Act: -0.0001

Data Index: 1052612 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1077807 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2147. Min Act: -0.0000

Data Index: 823083 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2188. Min Act: -0.0001

Data Index: 1562394 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2255. Min Act: -0.0000

Data Index: 43570 (C4 (Web Text))

Max Activating Token Index: 832