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

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

Neuron 3965 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0557. Min Range: -1.0557

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1524131 (Python Code)

Max Activating Token Index: 384

Text #1

Max Range: 1.0557. Min Range: -1.0557

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1501348 (Python Code)

Max Activating Token Index: 408

Text #2

Max Range: 1.0557. Min Range: -1.0557

Max Act: 1.0342. Min Act: -0.0000

Data Index: 1431911 (Python Code)

Max Activating Token Index: 765

Text #3

Max Range: 1.0557. Min Range: -1.0557

Max Act: 1.0557. Min Act: -0.0000

Data Index: 1452231 (Python Code)

Max Activating Token Index: 686

Text #4

Max Range: 1.0557. Min Range: -1.0557

Max Act: 1.0438. Min Act: -0.0000

Data Index: 1458691 (Python Code)

Max Activating Token Index: 357

Text #5

Max Range: 1.0557. Min Range: -1.0557

Max Act: 1.0093. Min Act: -0.0001

Data Index: 1537505 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1552247 (Python Code)

Max Activating Token Index: 194

Text #7

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.9640. Min Act: -0.0001

Data Index: 1588510 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1621120 (Python Code)

Max Activating Token Index: 490

Text #9

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1399528 (Python Code)

Max Activating Token Index: 770

Text #10

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.9351. Min Act: -0.0000

Data Index: 1593316 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1445790 (Python Code)

Max Activating Token Index: 257

Text #12

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.9566. Min Act: -0.0001

Data Index: 1645416 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1469281 (Python Code)

Max Activating Token Index: 370

Text #14

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.9518. Min Act: -0.0000

Data Index: 1648464 (Python Code)

Max Activating Token Index: 160

Text #15

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.9234. Min Act: -0.0000

Data Index: 1448317 (Python Code)

Max Activating Token Index: 249

Text #16

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1616218 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.9408. Min Act: -0.0001

Data Index: 1655128 (Python Code)

Max Activating Token Index: 822

Text #18

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1589977 (Python Code)

Max Activating Token Index: 911

Text #19

Max Range: 1.0557. Min Range: -1.0557

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1627608 (Python Code)

Max Activating Token Index: 196