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

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

Neuron 1221 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: 3.2457. Min Range: -3.2457

Max Act: 3.2457. Min Act: -0.1700

Data Index: 1175940 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.2142. Min Act: -0.1700

Data Index: 777226 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1828. Min Act: -0.1700

Data Index: 643070 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1985. Min Act: -0.1700

Data Index: 787395 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1355. Min Act: -0.1700

Data Index: 713967 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1670. Min Act: -0.1700

Data Index: 1190038 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1670. Min Act: -0.1700

Data Index: 1098959 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1355. Min Act: -0.1700

Data Index: 780421 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1198. Min Act: -0.1700

Data Index: 762234 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1355. Min Act: -0.1700

Data Index: 508765 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1040. Min Act: -0.1700

Data Index: 383326 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1040. Min Act: -0.1700

Data Index: 819638 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0882. Min Act: -0.1700

Data Index: 962744 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0882. Min Act: -0.1700

Data Index: 699034 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0725. Min Act: -0.1700

Data Index: 1213981 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0567. Min Act: -0.1700

Data Index: 142990 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0409. Min Act: -0.1700

Data Index: 1227967 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0567. Min Act: -0.1700

Data Index: 1146365 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0409. Min Act: -0.1700

Data Index: 1219973 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0725. Min Act: -0.1700

Data Index: 982498 (C4 (Web Text))

Max Activating Token Index: 750