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

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

Neuron 37 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0987. Min Range: -7.0987

Max Act: 7.0049. Min Act: -0.1700

Data Index: 1085259 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.9737. Min Act: -0.1700

Data Index: 182774 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 7.0987. Min Range: -7.0987

Max Act: 7.0674. Min Act: -0.1700

Data Index: 1042043 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.9737. Min Act: -0.1700

Data Index: 742664 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 7.0987. Min Range: -7.0987

Max Act: 7.0987. Min Act: -0.1700

Data Index: 212626 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.8799. Min Act: -0.1700

Data Index: 571225 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.9424. Min Act: -0.1700

Data Index: 26207 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.9112. Min Act: -0.1700

Data Index: 1046058 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.9424. Min Act: -0.1700

Data Index: 787713 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.9737. Min Act: -0.1700

Data Index: 782519 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.9424. Min Act: -0.1700

Data Index: 585849 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 7.0987. Min Range: -7.0987

Max Act: 7.0049. Min Act: -0.1700

Data Index: 932002 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.9112. Min Act: -0.1700

Data Index: 637650 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.9112. Min Act: -0.1700

Data Index: 1347179 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.8487. Min Act: -0.1700

Data Index: 568505 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.8799. Min Act: -0.1700

Data Index: 657906 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.9424. Min Act: -0.1700

Data Index: 393797 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.8487. Min Act: -0.1700

Data Index: 213675 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.9424. Min Act: -0.1700

Data Index: 335637 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 7.0987. Min Range: -7.0987

Max Act: 6.9112. Min Act: -0.1700

Data Index: 1308521 (C4 (Web Text))

Max Activating Token Index: 311