Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1297 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.7904. Min Act: -0.1700

Data Index: 1001832 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.7278. Min Act: -0.1700

Data Index: 49548 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6496. Min Act: -0.1700

Data Index: 323408 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6809. Min Act: -0.1700

Data Index: 749206 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6809. Min Act: -0.1700

Data Index: 764329 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6809. Min Act: -0.1700

Data Index: 920158 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6026. Min Act: -0.1700

Data Index: 287884 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6496. Min Act: -0.1700

Data Index: 387517 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.5870. Min Act: -0.1700

Data Index: 146196 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6183. Min Act: -0.1700

Data Index: 55606 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6026. Min Act: -0.1700

Data Index: 840129 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6339. Min Act: -0.1700

Data Index: 184716 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6026. Min Act: -0.1700

Data Index: 1048268 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6183. Min Act: -0.1700

Data Index: 950422 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6339. Min Act: -0.1700

Data Index: 357836 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.5870. Min Act: -0.1700

Data Index: 134241 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6653. Min Act: -0.1700

Data Index: 104598 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6026. Min Act: -0.1700

Data Index: 1188483 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.6026. Min Act: -0.1700

Data Index: 983023 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.5870. Min Act: -0.1700

Data Index: 16846 (C4 (Web Text))

Max Activating Token Index: 992