Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 944 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.4297. Min Act: -0.1700

Data Index: 1503714 (Python Code)

Max Activating Token Index: 444

Text #1

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.3047. Min Act: -0.1700

Data Index: 1567218 (Python Code)

Max Activating Token Index: 411

Text #2

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.3672. Min Act: -0.1700

Data Index: 1445224 (Python Code)

Max Activating Token Index: 654

Text #3

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.3360. Min Act: -0.1700

Data Index: 1583012 (Python Code)

Max Activating Token Index: 385

Text #4

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.3672. Min Act: -0.1700

Data Index: 1580009 (Python Code)

Max Activating Token Index: 783

Text #5

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.1797. Min Act: -0.1700

Data Index: 1577753 (Python Code)

Max Activating Token Index: 855

Text #6

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.0860. Min Act: -0.1700

Data Index: 1392795 (Python Code)

Max Activating Token Index: 332

Text #7

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.0860. Min Act: -0.1700

Data Index: 1361078 (Python Code)

Max Activating Token Index: 849

Text #8

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.1797. Min Act: -0.1700

Data Index: 1550937 (Python Code)

Max Activating Token Index: 947

Text #9

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.1172. Min Act: -0.1700

Data Index: 1543658 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.1172. Min Act: -0.1700

Data Index: 1613069 (Python Code)

Max Activating Token Index: 410

Text #11

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.1485. Min Act: -0.1700

Data Index: 1381541 (Python Code)

Max Activating Token Index: 925

Text #12

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.0547. Min Act: -0.1700

Data Index: 1612926 (Python Code)

Max Activating Token Index: 788

Text #13

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.0860. Min Act: -0.1700

Data Index: 1387437 (Python Code)

Max Activating Token Index: 508

Text #14

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.0547. Min Act: -0.1700

Data Index: 1551407 (Python Code)

Max Activating Token Index: 407

Text #15

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.0860. Min Act: -0.1700

Data Index: 1454782 (Python Code)

Max Activating Token Index: 968

Text #16

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.0547. Min Act: -0.1700

Data Index: 1389328 (Python Code)

Max Activating Token Index: 104

Text #17

Max Range: 5.4297. Min Range: -5.4297

Max Act: 4.9610. Min Act: -0.1700

Data Index: 1610433 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.0547. Min Act: -0.1700

Data Index: 1387933 (Python Code)

Max Activating Token Index: 781

Text #19

Max Range: 5.4297. Min Range: -5.4297

Max Act: 5.0547. Min Act: -0.1700

Data Index: 1426575 (Python Code)

Max Activating Token Index: 1007