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

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

Neuron 2047 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.3489. Min Act: -0.1700

Data Index: 141180 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.2864. Min Act: -0.1700

Data Index: 826652 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.2239. Min Act: -0.1700

Data Index: 471638 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.1926. Min Act: -0.1700

Data Index: 1237917 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.1614. Min Act: -0.1700

Data Index: 174136 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.1301. Min Act: -0.1700

Data Index: 595126 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.0989. Min Act: -0.1700

Data Index: 455300 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.1301. Min Act: -0.1700

Data Index: 1199308 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.0989. Min Act: -0.1700

Data Index: 306506 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.0989. Min Act: -0.1700

Data Index: 31430 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.0676. Min Act: -0.1700

Data Index: 111965 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.0676. Min Act: -0.1700

Data Index: 477973 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.0364. Min Act: -0.1700

Data Index: 1357806 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.0364. Min Act: -0.1700

Data Index: 391931 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.0364. Min Act: -0.1700

Data Index: 519879 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.0364. Min Act: -0.1699

Data Index: 148085 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 5.3489. Min Range: -5.3489

Max Act: 4.9739. Min Act: -0.1700

Data Index: 613425 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.0364. Min Act: -0.1700

Data Index: 885303 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.0364. Min Act: -0.1700

Data Index: 462760 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 5.3489. Min Range: -5.3489

Max Act: 5.0051. Min Act: -0.1700

Data Index: 748622 (C4 (Web Text))

Max Activating Token Index: 722