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

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

Neuron 1195 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: 5.6474. Min Range: -5.6474

Max Act: 5.6474. Min Act: -0.1700

Data Index: 537777 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.5849. Min Act: -0.1700

Data Index: 793618 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.5224. Min Act: -0.1700

Data Index: 1333647 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.5224. Min Act: -0.1700

Data Index: 550134 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.4911. Min Act: -0.1700

Data Index: 884494 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.4599. Min Act: -0.1700

Data Index: 522785 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.4286. Min Act: -0.1700

Data Index: 713622 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.4286. Min Act: -0.1700

Data Index: 43548 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.3974. Min Act: -0.1700

Data Index: 1300399 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.4599. Min Act: -0.1700

Data Index: 449969 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.3974. Min Act: -0.1700

Data Index: 171876 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.4286. Min Act: -0.1700

Data Index: 235271 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.3661. Min Act: -0.1700

Data Index: 215896 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.3661. Min Act: -0.1700

Data Index: 62261 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.3349. Min Act: -0.1700

Data Index: 1055008 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.3036. Min Act: -0.1700

Data Index: 136369 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.3036. Min Act: -0.1700

Data Index: 120224 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.3661. Min Act: -0.1700

Data Index: 877410 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.2724. Min Act: -0.1700

Data Index: 424338 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 5.6474. Min Range: -5.6474

Max Act: 5.3036. Min Act: -0.1700

Data Index: 512788 (C4 (Web Text))

Max Activating Token Index: 779