Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1200 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.2302. Min Act: -0.1700

Data Index: 1232933 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.1830. Min Act: -0.1700

Data Index: 693541 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.1515. Min Act: -0.1700

Data Index: 1164308 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.1515. Min Act: -0.1700

Data Index: 748894 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.1357. Min Act: -0.1700

Data Index: 566250 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.1357. Min Act: -0.1700

Data Index: 152710 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.1515. Min Act: -0.1700

Data Index: 926593 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.1042. Min Act: -0.1700

Data Index: 307283 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.1042. Min Act: -0.1700

Data Index: 344295 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.0884. Min Act: -0.1700

Data Index: 761065 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.0884. Min Act: -0.1700

Data Index: 143306 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.0884. Min Act: -0.1700

Data Index: 657527 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.1042. Min Act: -0.1700

Data Index: 1010328 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.1200. Min Act: -0.1700

Data Index: 1024592 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.0884. Min Act: -0.1700

Data Index: 786072 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.1200. Min Act: -0.1700

Data Index: 713232 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.0727. Min Act: -0.1700

Data Index: 271677 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.0884. Min Act: -0.1700

Data Index: 1131083 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.0569. Min Act: -0.1700

Data Index: 187008 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 3.2302. Min Range: -3.2302

Max Act: 3.0569. Min Act: -0.1700

Data Index: 233873 (C4 (Web Text))

Max Activating Token Index: 69