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

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

Neuron 1118 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: 5.6684. Min Range: -5.6684

Max Act: 5.6684. Min Act: -0.1700

Data Index: 1220497 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.4809. Min Act: -0.1700

Data Index: 470891 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.4809. Min Act: -0.1700

Data Index: 851982 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.4497. Min Act: -0.1700

Data Index: 394846 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.4184. Min Act: -0.1700

Data Index: 1275722 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.4184. Min Act: -0.1700

Data Index: 123077 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.4184. Min Act: -0.1700

Data Index: 818127 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.4184. Min Act: -0.1700

Data Index: 1287751 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.3872. Min Act: -0.1700

Data Index: 1123980 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.4184. Min Act: -0.1700

Data Index: 1159505 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.4184. Min Act: -0.1700

Data Index: 725982 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.3872. Min Act: -0.1700

Data Index: 427844 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.3247. Min Act: -0.1700

Data Index: 140912 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.3559. Min Act: -0.1700

Data Index: 463914 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.3559. Min Act: -0.1700

Data Index: 674084 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.3247. Min Act: -0.1700

Data Index: 463470 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.3872. Min Act: -0.1700

Data Index: 1211466 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.3559. Min Act: -0.1700

Data Index: 801308 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.3247. Min Act: -0.1700

Data Index: 15502 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 5.6684. Min Range: -5.6684

Max Act: 5.2934. Min Act: -0.1700

Data Index: 10035 (C4 (Web Text))

Max Activating Token Index: 732