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

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

Neuron 722 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.3761. Min Act: -0.1700

Data Index: 841957 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.2976. Min Act: -0.1700

Data Index: 719197 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.2033. Min Act: -0.1700

Data Index: 276895 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.2505. Min Act: -0.1700

Data Index: 232139 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.3133. Min Act: -0.1700

Data Index: 266487 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.2662. Min Act: -0.1700

Data Index: 1275590 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.2191. Min Act: -0.1700

Data Index: 540087 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.1876. Min Act: -0.1700

Data Index: 130538 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.2348. Min Act: -0.1700

Data Index: 580739 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.2819. Min Act: -0.1700

Data Index: 187879 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.2191. Min Act: -0.1700

Data Index: 1332653 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.2033. Min Act: -0.1700

Data Index: 391524 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.2348. Min Act: -0.1700

Data Index: 1262189 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.1404. Min Act: -0.1700

Data Index: 371917 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.1719. Min Act: -0.1700

Data Index: 129689 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.2191. Min Act: -0.1700

Data Index: 1215132 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.1719. Min Act: -0.1700

Data Index: 582537 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.1719. Min Act: -0.1700

Data Index: 1171623 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.1561. Min Act: -0.1700

Data Index: 1333029 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.1088. Min Act: -0.1700

Data Index: 1451159 (Python Code)

Max Activating Token Index: 565