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

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

Neuron 1448 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: 3.3568. Min Range: -3.3568

Max Act: 3.3568. Min Act: -0.1700

Data Index: 785810 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.3097. Min Act: -0.1700

Data Index: 186027 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2468. Min Act: -0.1700

Data Index: 723554 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2311. Min Act: -0.1700

Data Index: 937133 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2311. Min Act: -0.1700

Data Index: 1409769 (Python Code)

Max Activating Token Index: 962

Text #5

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1682. Min Act: -0.1700

Data Index: 1596132 (Python Code)

Max Activating Token Index: 449

Text #6

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1524. Min Act: -0.1700

Data Index: 1322001 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1524. Min Act: -0.1700

Data Index: 70030 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1524. Min Act: -0.1700

Data Index: 1448518 (Python Code)

Max Activating Token Index: 598

Text #9

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1524. Min Act: -0.1700

Data Index: 1417639 (Python Code)

Max Activating Token Index: 614

Text #10

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1367. Min Act: -0.1700

Data Index: 1404748 (Python Code)

Max Activating Token Index: 495

Text #11

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1524. Min Act: -0.1700

Data Index: 274870 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1367. Min Act: -0.1700

Data Index: 1415087 (Python Code)

Max Activating Token Index: 448

Text #13

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1367. Min Act: -0.1700

Data Index: 1579085 (Python Code)

Max Activating Token Index: 968

Text #14

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1367. Min Act: -0.1700

Data Index: 1409095 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1052. Min Act: -0.1700

Data Index: 1597946 (Python Code)

Max Activating Token Index: 368

Text #16

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1209. Min Act: -0.1700

Data Index: 1469040 (Python Code)

Max Activating Token Index: 764

Text #17

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1209. Min Act: -0.1700

Data Index: 1396866 (Python Code)

Max Activating Token Index: 432

Text #18

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1209. Min Act: -0.1700

Data Index: 139977 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1209. Min Act: -0.1700

Data Index: 1354559 (C4 (Web Text))

Max Activating Token Index: 519