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

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

Neuron 1482 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: 5.6238. Min Range: -5.6238

Max Act: 5.6238. Min Act: -0.1700

Data Index: 401316 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.5456. Min Act: -0.1700

Data Index: 837403 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.5769. Min Act: -0.1700

Data Index: 1095035 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.5300. Min Act: -0.1700

Data Index: 1233566 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4988. Min Act: -0.1700

Data Index: 962075 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4675. Min Act: -0.1700

Data Index: 467866 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4519. Min Act: -0.1700

Data Index: 1275722 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4519. Min Act: -0.1700

Data Index: 277032 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4206. Min Act: -0.1700

Data Index: 979089 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4363. Min Act: -0.1700

Data Index: 936264 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4050. Min Act: -0.1700

Data Index: 295932 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4050. Min Act: -0.1700

Data Index: 221928 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.3894. Min Act: -0.1700

Data Index: 861066 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.4050. Min Act: -0.1700

Data Index: 1214907 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.3894. Min Act: -0.1700

Data Index: 531403 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.3894. Min Act: -0.1700

Data Index: 204751 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.3738. Min Act: -0.1700

Data Index: 592 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.3581. Min Act: -0.1700

Data Index: 792573 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.3269. Min Act: -0.1700

Data Index: 951522 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 5.6238. Min Range: -5.6238

Max Act: 5.3581. Min Act: -0.1700

Data Index: 559456 (C4 (Web Text))

Max Activating Token Index: 715