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

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

Neuron 1437 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: 3.4964. Min Range: -3.4964

Max Act: 3.4964. Min Act: -0.1700

Data Index: 727803 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.4023. Min Act: -0.1700

Data Index: 313413 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.4023. Min Act: -0.1700

Data Index: 660100 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.3239. Min Act: -0.1700

Data Index: 621046 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.3082. Min Act: -0.1700

Data Index: 252329 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.3082. Min Act: -0.1700

Data Index: 995600 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2925. Min Act: -0.1700

Data Index: 656765 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.3082. Min Act: -0.1700

Data Index: 453004 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2925. Min Act: -0.1700

Data Index: 1052206 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2925. Min Act: -0.1700

Data Index: 24543 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.3082. Min Act: -0.1700

Data Index: 1324236 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2611. Min Act: -0.1700

Data Index: 1253647 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2768. Min Act: -0.1700

Data Index: 640872 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2453. Min Act: -0.1700

Data Index: 268564 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2453. Min Act: -0.1700

Data Index: 650573 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2453. Min Act: -0.1700

Data Index: 1311110 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2453. Min Act: -0.1700

Data Index: 1280220 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2453. Min Act: -0.1700

Data Index: 641943 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2139. Min Act: -0.1700

Data Index: 962554 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.1982. Min Act: -0.1700

Data Index: 231425 (C4 (Web Text))

Max Activating Token Index: 280