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

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

Neuron 3974 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8794. Min Act: -0.0001

Data Index: 1526535 (Python Code)

Max Activating Token Index: 897

Text #1

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1606656 (Python Code)

Max Activating Token Index: 574

Text #2

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1639022 (Python Code)

Max Activating Token Index: 243

Text #3

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.9403. Min Act: -0.0000

Data Index: 1491233 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1542639 (Python Code)

Max Activating Token Index: 348

Text #5

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1549358 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1503713 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1400050 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1620233 (Python Code)

Max Activating Token Index: 692

Text #9

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1373641 (Python Code)

Max Activating Token Index: 926

Text #10

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1651942 (Python Code)

Max Activating Token Index: 802

Text #11

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1424037 (Python Code)

Max Activating Token Index: 875

Text #12

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1465038 (Python Code)

Max Activating Token Index: 126

Text #13

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1577159 (Python Code)

Max Activating Token Index: 269

Text #14

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1563201 (Python Code)

Max Activating Token Index: 445

Text #15

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1375385 (Python Code)

Max Activating Token Index: 493

Text #16

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1525868 (Python Code)

Max Activating Token Index: 947

Text #17

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1482129 (Python Code)

Max Activating Token Index: 798

Text #18

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1504252 (Python Code)

Max Activating Token Index: 550

Text #19

Max Range: 0.9403. Min Range: -0.9403

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1473452 (Python Code)

Max Activating Token Index: 984