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

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

Neuron 5489 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.8220. Min Act: -0.0000

Data Index: 1651025 (Python Code)

Max Activating Token Index: 781

Text #1

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.7249. Min Act: -0.0000

Data Index: 1378177 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.5811. Min Act: -0.0000

Data Index: 1613232 (Python Code)

Max Activating Token Index: 683

Text #3

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.7060. Min Act: -0.0000

Data Index: 1455939 (Python Code)

Max Activating Token Index: 759

Text #4

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.4912. Min Act: -0.0000

Data Index: 1611001 (Python Code)

Max Activating Token Index: 361

Text #5

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.5779. Min Act: -0.0000

Data Index: 1430783 (Python Code)

Max Activating Token Index: 855

Text #6

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.5630. Min Act: -0.0000

Data Index: 1486411 (Python Code)

Max Activating Token Index: 502

Text #7

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1406013 (Python Code)

Max Activating Token Index: 234

Text #8

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.4380. Min Act: -0.0000

Data Index: 1426627 (Python Code)

Max Activating Token Index: 315

Text #9

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.3463. Min Act: -0.0000

Data Index: 1468866 (Python Code)

Max Activating Token Index: 459

Text #10

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.2884. Min Act: -0.0000

Data Index: 1598249 (Python Code)

Max Activating Token Index: 371

Text #11

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.3660. Min Act: -0.0000

Data Index: 1648019 (Python Code)

Max Activating Token Index: 626

Text #12

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1379903 (Python Code)

Max Activating Token Index: 792

Text #13

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.2877. Min Act: -0.0000

Data Index: 1547511 (Python Code)

Max Activating Token Index: 178

Text #14

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.2911. Min Act: -0.0000

Data Index: 1563738 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.2335. Min Act: -0.0000

Data Index: 1370453 (Python Code)

Max Activating Token Index: 336

Text #16

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.3282. Min Act: -0.0000

Data Index: 1651259 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.3236. Min Act: -0.0000

Data Index: 1469905 (Python Code)

Max Activating Token Index: 556

Text #18

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.1616. Min Act: -0.0000

Data Index: 1495500 (Python Code)

Max Activating Token Index: 358

Text #19

Max Range: 1.8220. Min Range: -1.8220

Max Act: 1.1829. Min Act: -0.0000

Data Index: 1571917 (Python Code)

Max Activating Token Index: 966