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

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

Neuron 3116 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: 0.4344. Min Range: -0.4344

Max Act: 0.4344. Min Act: -0.0002

Data Index: 1561152 (Python Code)

Max Activating Token Index: 543

Text #1

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4119. Min Act: -0.0002

Data Index: 1382966 (Python Code)

Max Activating Token Index: 472

Text #2

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3968. Min Act: -0.0002

Data Index: 1421657 (Python Code)

Max Activating Token Index: 611

Text #3

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3862. Min Act: -0.0002

Data Index: 1594635 (Python Code)

Max Activating Token Index: 395

Text #4

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3821. Min Act: -0.0002

Data Index: 1487057 (Python Code)

Max Activating Token Index: 1016

Text #5

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3813. Min Act: -0.0002

Data Index: 1438503 (Python Code)

Max Activating Token Index: 591

Text #6

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3561. Min Act: -0.0002

Data Index: 1502277 (Python Code)

Max Activating Token Index: 669

Text #7

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3491. Min Act: -0.0002

Data Index: 1560072 (Python Code)

Max Activating Token Index: 392

Text #8

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3436. Min Act: -0.0002

Data Index: 1429586 (Python Code)

Max Activating Token Index: 525

Text #9

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3441. Min Act: -0.0002

Data Index: 1379188 (Python Code)

Max Activating Token Index: 541

Text #10

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3414. Min Act: -0.0002

Data Index: 1637019 (Python Code)

Max Activating Token Index: 491

Text #11

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3259. Min Act: -0.0002

Data Index: 1366424 (Python Code)

Max Activating Token Index: 979

Text #12

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3345. Min Act: -0.0002

Data Index: 1500962 (Python Code)

Max Activating Token Index: 364

Text #13

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3274. Min Act: -0.0002

Data Index: 1576451 (Python Code)

Max Activating Token Index: 307

Text #14

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3296. Min Act: -0.0002

Data Index: 1635659 (Python Code)

Max Activating Token Index: 999

Text #15

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3304. Min Act: -0.0002

Data Index: 1574040 (Python Code)

Max Activating Token Index: 405

Text #16

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3235. Min Act: -0.0002

Data Index: 1413330 (Python Code)

Max Activating Token Index: 446

Text #17

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3155. Min Act: -0.0002

Data Index: 1414011 (Python Code)

Max Activating Token Index: 700

Text #18

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3225. Min Act: -0.0002

Data Index: 1564767 (Python Code)

Max Activating Token Index: 752

Text #19

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3071. Min Act: -0.0002

Data Index: 1433669 (Python Code)

Max Activating Token Index: 635