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

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

Neuron 363 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: 3.5694. Min Range: -3.5694

Max Act: 3.5537. Min Act: -0.1700

Data Index: 1147359 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.5380. Min Act: -0.1700

Data Index: 276415 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.5224. Min Act: -0.1700

Data Index: 306135 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.5224. Min Act: -0.1700

Data Index: 497639 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.5694. Min Act: -0.1700

Data Index: 713194 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.5067. Min Act: -0.1700

Data Index: 629578 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.4754. Min Act: -0.1700

Data Index: 961832 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.4283. Min Act: -0.1700

Data Index: 1581039 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.4597. Min Act: -0.1700

Data Index: 957651 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.4440. Min Act: -0.1700

Data Index: 6862 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.4283. Min Act: -0.1700

Data Index: 175573 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.3970. Min Act: -0.1700

Data Index: 725840 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.4440. Min Act: -0.1700

Data Index: 210891 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.4440. Min Act: -0.1700

Data Index: 492832 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.3499. Min Act: -0.1700

Data Index: 715974 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.3970. Min Act: -0.1700

Data Index: 454131 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.3970. Min Act: -0.1700

Data Index: 442790 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.3656. Min Act: -0.1700

Data Index: 1252453 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.3813. Min Act: -0.1700

Data Index: 1101480 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 3.5694. Min Range: -3.5694

Max Act: 3.3970. Min Act: -0.1700

Data Index: 606513 (C4 (Web Text))

Max Activating Token Index: 955