Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1091 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7491. Min Act: -0.1700

Data Index: 1511308 (Python Code)

Max Activating Token Index: 598

Text #1

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7491. Min Act: -0.1700

Data Index: 1444731 (Python Code)

Max Activating Token Index: 755

Text #2

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7334. Min Act: -0.1700

Data Index: 1638914 (Python Code)

Max Activating Token Index: 755

Text #3

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7334. Min Act: -0.1700

Data Index: 1460505 (Python Code)

Max Activating Token Index: 545

Text #4

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7334. Min Act: -0.1700

Data Index: 1571728 (Python Code)

Max Activating Token Index: 620

Text #5

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7334. Min Act: -0.1700

Data Index: 1487463 (Python Code)

Max Activating Token Index: 363

Text #6

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7334. Min Act: -0.1700

Data Index: 1515002 (Python Code)

Max Activating Token Index: 541

Text #7

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7334. Min Act: -0.1700

Data Index: 727411 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7178. Min Act: -0.1700

Data Index: 1558722 (Python Code)

Max Activating Token Index: 727

Text #9

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7178. Min Act: -0.1700

Data Index: 1365467 (Python Code)

Max Activating Token Index: 500

Text #10

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1413690 (Python Code)

Max Activating Token Index: 690

Text #11

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1546980 (Python Code)

Max Activating Token Index: 617

Text #12

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1408272 (Python Code)

Max Activating Token Index: 500

Text #13

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6865. Min Act: -0.1700

Data Index: 1544328 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6865. Min Act: -0.1700

Data Index: 1491642 (Python Code)

Max Activating Token Index: 243

Text #15

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6865. Min Act: -0.1700

Data Index: 1503481 (Python Code)

Max Activating Token Index: 851

Text #16

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1589705 (Python Code)

Max Activating Token Index: 520

Text #17

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6708. Min Act: -0.1700

Data Index: 1432097 (Python Code)

Max Activating Token Index: 589

Text #18

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6865. Min Act: -0.1700

Data Index: 1390464 (Python Code)

Max Activating Token Index: 844

Text #19

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6552. Min Act: -0.1700

Data Index: 1478077 (Python Code)

Max Activating Token Index: 347