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

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

Neuron 292 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2575. Min Range: -5.2575

Max Act: 5.2262. Min Act: -0.1700

Data Index: 1648919 (Python Code)

Max Activating Token Index: 728

Text #1

Max Range: 5.2575. Min Range: -5.2575

Max Act: 5.2262. Min Act: -0.1700

Data Index: 1506899 (Python Code)

Max Activating Token Index: 298

Text #2

Max Range: 5.2575. Min Range: -5.2575

Max Act: 5.2575. Min Act: -0.1700

Data Index: 1513476 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 5.2575. Min Range: -5.2575

Max Act: 5.0700. Min Act: -0.1700

Data Index: 1364817 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 5.2575. Min Range: -5.2575

Max Act: 5.0075. Min Act: -0.1700

Data Index: 1586183 (Python Code)

Max Activating Token Index: 847

Text #5

Max Range: 5.2575. Min Range: -5.2575

Max Act: 5.0075. Min Act: -0.1700

Data Index: 1431033 (Python Code)

Max Activating Token Index: 945

Text #6

Max Range: 5.2575. Min Range: -5.2575

Max Act: 5.0700. Min Act: -0.1700

Data Index: 1404538 (Python Code)

Max Activating Token Index: 456

Text #7

Max Range: 5.2575. Min Range: -5.2575

Max Act: 5.0387. Min Act: -0.1699

Data Index: 1475131 (Python Code)

Max Activating Token Index: 215

Text #8

Max Range: 5.2575. Min Range: -5.2575

Max Act: 4.9762. Min Act: -0.1700

Data Index: 1616360 (Python Code)

Max Activating Token Index: 225

Text #9

Max Range: 5.2575. Min Range: -5.2575

Max Act: 4.9762. Min Act: -0.1699

Data Index: 1619094 (Python Code)

Max Activating Token Index: 148

Text #10

Max Range: 5.2575. Min Range: -5.2575

Max Act: 4.9137. Min Act: -0.1700

Data Index: 1394904 (Python Code)

Max Activating Token Index: 861

Text #11

Max Range: 5.2575. Min Range: -5.2575

Max Act: 4.9137. Min Act: -0.1700

Data Index: 1430298 (Python Code)

Max Activating Token Index: 372

Text #12

Max Range: 5.2575. Min Range: -5.2575

Max Act: 4.8200. Min Act: -0.1700

Data Index: 1443972 (Python Code)

Max Activating Token Index: 443

Text #13

Max Range: 5.2575. Min Range: -5.2575

Max Act: 4.8200. Min Act: -0.1700

Data Index: 1480375 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 5.2575. Min Range: -5.2575

Max Act: 4.7887. Min Act: -0.1699

Data Index: 1481471 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 5.2575. Min Range: -5.2575

Max Act: 4.7575. Min Act: -0.1700

Data Index: 1534376 (Python Code)

Max Activating Token Index: 698

Text #16

Max Range: 5.2575. Min Range: -5.2575

Max Act: 4.8512. Min Act: -0.1699

Data Index: 1441280 (Python Code)

Max Activating Token Index: 877

Text #17

Max Range: 5.2575. Min Range: -5.2575

Max Act: 4.8200. Min Act: -0.1699

Data Index: 1541383 (Python Code)

Max Activating Token Index: 110

Text #18

Max Range: 5.2575. Min Range: -5.2575

Max Act: 4.6325. Min Act: -0.1700

Data Index: 1567564 (Python Code)

Max Activating Token Index: 653

Text #19

Max Range: 5.2575. Min Range: -5.2575

Max Act: 4.7262. Min Act: -0.1699

Data Index: 1586069 (Python Code)

Max Activating Token Index: 371