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

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

Neuron 1352 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.9762. Min Act: -0.1700

Data Index: 1057665 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.9137. Min Act: -0.1700

Data Index: 1051518 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.9762. Min Act: -0.1700

Data Index: 1026816 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.8512. Min Act: -0.1700

Data Index: 97534 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.7262. Min Act: -0.1700

Data Index: 997274 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.7574. Min Act: -0.1700

Data Index: 696641 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.6949. Min Act: -0.1700

Data Index: 1047168 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.6949. Min Act: -0.1700

Data Index: 908410 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.6949. Min Act: -0.1700

Data Index: 472068 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.6324. Min Act: -0.1700

Data Index: 905823 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.6324. Min Act: -0.1700

Data Index: 1054275 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.6012. Min Act: -0.1700

Data Index: 70899 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.6012. Min Act: -0.1700

Data Index: 1113853 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.5699. Min Act: -0.1700

Data Index: 686713 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.5074. Min Act: -0.1700

Data Index: 177370 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.5387. Min Act: -0.1700

Data Index: 1070329 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.4449. Min Act: -0.1700

Data Index: 803399 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.4137. Min Act: -0.1700

Data Index: 553950 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.3824. Min Act: -0.1700

Data Index: 845173 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 5.9762. Min Range: -5.9762

Max Act: 5.3824. Min Act: -0.1700

Data Index: 48843 (C4 (Web Text))

Max Activating Token Index: 426