Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 212 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7498. Min Act: -0.0001

Data Index: 1456474 (Python Code)

Max Activating Token Index: 105

Text #1

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7003. Min Act: -0.0001

Data Index: 1641831 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6380. Min Act: -0.0001

Data Index: 1390763 (Python Code)

Max Activating Token Index: 726

Text #3

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5795. Min Act: -0.0001

Data Index: 1640252 (Python Code)

Max Activating Token Index: 1004

Text #4

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5168. Min Act: -0.0001

Data Index: 1559413 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5656. Min Act: -0.0001

Data Index: 1393670 (Python Code)

Max Activating Token Index: 21

Text #6

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6417. Min Act: -0.0001

Data Index: 1596228 (Python Code)

Max Activating Token Index: 796

Text #7

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5818. Min Act: -0.0001

Data Index: 1530706 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5449. Min Act: -0.0001

Data Index: 1643411 (Python Code)

Max Activating Token Index: 455

Text #9

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5541. Min Act: -0.0001

Data Index: 1365727 (Python Code)

Max Activating Token Index: 588

Text #10

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5509. Min Act: -0.0001

Data Index: 1558357 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5534. Min Act: -0.0001

Data Index: 1543389 (Python Code)

Max Activating Token Index: 336

Text #12

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.4733. Min Act: -0.0001

Data Index: 1472251 (Python Code)

Max Activating Token Index: 528

Text #13

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5134. Min Act: -0.0001

Data Index: 1495872 (Python Code)

Max Activating Token Index: 409

Text #14

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5637. Min Act: -0.0001

Data Index: 1398463 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5154. Min Act: -0.0001

Data Index: 1572240 (Python Code)

Max Activating Token Index: 570

Text #16

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5439. Min Act: -0.0001

Data Index: 1530443 (Python Code)

Max Activating Token Index: 465

Text #17

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5121. Min Act: -0.0001

Data Index: 1532471 (Python Code)

Max Activating Token Index: 723

Text #18

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5236. Min Act: -0.0001

Data Index: 1386725 (Python Code)

Max Activating Token Index: 901

Text #19

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.4829. Min Act: -0.0001

Data Index: 1392109 (Python Code)

Max Activating Token Index: 455