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

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

Neuron 205 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: 5.7096. Min Range: -5.7096

Max Act: 5.7096. Min Act: -0.1700

Data Index: 896138 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.6471. Min Act: -0.1700

Data Index: 547731 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.6784. Min Act: -0.1700

Data Index: 978640 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.5846. Min Act: -0.1700

Data Index: 766925 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.6159. Min Act: -0.1700

Data Index: 957380 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.5221. Min Act: -0.1700

Data Index: 307913 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.4596. Min Act: -0.1700

Data Index: 1135396 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3971. Min Act: -0.1700

Data Index: 976491 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3971. Min Act: -0.1700

Data Index: 482382 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3346. Min Act: -0.1700

Data Index: 1138587 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.4596. Min Act: -0.1700

Data Index: 161317 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3659. Min Act: -0.1700

Data Index: 663130 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3346. Min Act: -0.1700

Data Index: 846012 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3659. Min Act: -0.1700

Data Index: 706619 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3346. Min Act: -0.1700

Data Index: 932603 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.2721. Min Act: -0.1700

Data Index: 335363 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.2721. Min Act: -0.1700

Data Index: 1216062 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3034. Min Act: -0.1700

Data Index: 392550 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.3034. Min Act: -0.1700

Data Index: 910255 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 5.7096. Min Range: -5.7096

Max Act: 5.1784. Min Act: -0.1700

Data Index: 907616 (C4 (Web Text))

Max Activating Token Index: 363