Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2741 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1362478 (Python Code)

Max Activating Token Index: 837

Text #1

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1423598 (Python Code)

Max Activating Token Index: 632

Text #2

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1515658 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1365420 (Python Code)

Max Activating Token Index: 186

Text #4

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1253763 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1596900 (Python Code)

Max Activating Token Index: 810

Text #6

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1417338 (Python Code)

Max Activating Token Index: 631

Text #7

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1296948 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1527058 (Python Code)

Max Activating Token Index: 433

Text #9

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1526983 (Python Code)

Max Activating Token Index: 757

Text #10

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0426. Min Act: -0.0002

Data Index: 595750 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1534528 (Python Code)

Max Activating Token Index: 461

Text #12

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1607980 (Python Code)

Max Activating Token Index: 766

Text #13

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0420. Min Act: -0.0002

Data Index: 721504 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1615921 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1504474 (Python Code)

Max Activating Token Index: 772

Text #16

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1409290 (Python Code)

Max Activating Token Index: 792

Text #17

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0419. Min Act: -0.0002

Data Index: 699083 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1412351 (Python Code)

Max Activating Token Index: 603

Text #19

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1457851 (Python Code)

Max Activating Token Index: 174