Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1906 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0458. Min Act: -0.0003

Data Index: 50283 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0003

Data Index: 570398 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1359652 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1368770 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0413. Min Act: -0.0003

Data Index: 692031 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1495406 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1352685 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1417544 (Python Code)

Max Activating Token Index: 39

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0351. Min Act: -0.0003

Data Index: 400722 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0402. Min Act: -0.0003

Data Index: 1492885 (Python Code)

Max Activating Token Index: 257

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0411. Min Act: -0.0003

Data Index: 1535970 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0388. Min Act: -0.0003

Data Index: 1462201 (Python Code)

Max Activating Token Index: 694

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1570997 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0402. Min Act: -0.0003

Data Index: 1387467 (Python Code)

Max Activating Token Index: 117

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1502691 (Python Code)

Max Activating Token Index: 138

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1548299 (Python Code)

Max Activating Token Index: 230

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1489510 (Python Code)

Max Activating Token Index: 269

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0395. Min Act: -0.0003

Data Index: 1445564 (Python Code)

Max Activating Token Index: 256

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1303869 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1414656 (Python Code)

Max Activating Token Index: 833