Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2425 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3754. Min Act: -0.0002

Data Index: 21241 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3499. Min Act: -0.0002

Data Index: 940234 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3527. Min Act: -0.0002

Data Index: 1558225 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3338. Min Act: -0.0002

Data Index: 685257 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3283. Min Act: -0.0002

Data Index: 1305718 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3328. Min Act: -0.0002

Data Index: 1087373 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3336. Min Act: -0.0002

Data Index: 1614769 (Python Code)

Max Activating Token Index: 277

Text #7

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3227. Min Act: -0.0002

Data Index: 146327 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3289. Min Act: -0.0002

Data Index: 1233693 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3277. Min Act: -0.0002

Data Index: 1193768 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3172. Min Act: -0.0002

Data Index: 1374961 (Python Code)

Max Activating Token Index: 836

Text #11

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3178. Min Act: -0.0002

Data Index: 1611445 (Python Code)

Max Activating Token Index: 404

Text #12

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3171. Min Act: -0.0003

Data Index: 574462 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3181. Min Act: -0.0002

Data Index: 1556959 (Python Code)

Max Activating Token Index: 356

Text #14

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3189. Min Act: -0.0002

Data Index: 223525 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3181. Min Act: -0.0002

Data Index: 1154504 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3114. Min Act: -0.0002

Data Index: 1483899 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3068. Min Act: -0.0002

Data Index: 1450247 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3095. Min Act: -0.0002

Data Index: 1387713 (Python Code)

Max Activating Token Index: 301

Text #19

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3114. Min Act: -0.0002

Data Index: 847169 (C4 (Web Text))

Max Activating Token Index: 512