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

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

Neuron 1207 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4665. Min Range: -5.4665

Max Act: 5.4665. Min Act: -0.1700

Data Index: 1118431 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 5.4665. Min Range: -5.4665

Max Act: 5.3102. Min Act: -0.1700

Data Index: 532989 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 5.4665. Min Range: -5.4665

Max Act: 5.0602. Min Act: -0.1700

Data Index: 1332536 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 5.4665. Min Range: -5.4665

Max Act: 5.0602. Min Act: -0.1700

Data Index: 883162 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 5.4665. Min Range: -5.4665

Max Act: 5.0290. Min Act: -0.1700

Data Index: 1052396 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.9977. Min Act: -0.1700

Data Index: 1055294 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.9352. Min Act: -0.1700

Data Index: 335513 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 5.4665. Min Range: -5.4665

Max Act: 5.0290. Min Act: -0.1700

Data Index: 1204497 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.9665. Min Act: -0.1700

Data Index: 32594 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.9040. Min Act: -0.1700

Data Index: 885645 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.9040. Min Act: -0.1700

Data Index: 3753 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.9352. Min Act: -0.1700

Data Index: 118703 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.9040. Min Act: -0.1700

Data Index: 66638 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.8727. Min Act: -0.1700

Data Index: 821478 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.8727. Min Act: -0.1700

Data Index: 954206 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.9040. Min Act: -0.1700

Data Index: 575736 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.8415. Min Act: -0.1700

Data Index: 475523 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.8415. Min Act: -0.1700

Data Index: 1251269 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.8102. Min Act: -0.1700

Data Index: 1080317 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 5.4665. Min Range: -5.4665

Max Act: 4.7790. Min Act: -0.1700

Data Index: 171876 (C4 (Web Text))

Max Activating Token Index: 404