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

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

Neuron 1710 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.6144. Min Act: -0.1700

Data Index: 434153 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.3637. Min Act: -0.1700

Data Index: 984465 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.3794. Min Act: -0.1700

Data Index: 1300933 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.3009. Min Act: -0.1700

Data Index: 414272 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.3009. Min Act: -0.1700

Data Index: 211291 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.3009. Min Act: -0.1700

Data Index: 833764 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.2852. Min Act: -0.1700

Data Index: 874032 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.3009. Min Act: -0.1700

Data Index: 338756 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.2380. Min Act: -0.1700

Data Index: 488464 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.2695. Min Act: -0.1700

Data Index: 790525 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.2852. Min Act: -0.1700

Data Index: 647188 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.2695. Min Act: -0.1700

Data Index: 1259745 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.2223. Min Act: -0.1700

Data Index: 180332 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.2066. Min Act: -0.1700

Data Index: 153300 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.2066. Min Act: -0.1700

Data Index: 227912 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.2223. Min Act: -0.1700

Data Index: 767478 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.2223. Min Act: -0.1700

Data Index: 1114758 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.1594. Min Act: -0.1700

Data Index: 1343863 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.1751. Min Act: -0.1700

Data Index: 457004 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 3.6144. Min Range: -3.6144

Max Act: 3.1436. Min Act: -0.1700

Data Index: 1022406 (C4 (Web Text))

Max Activating Token Index: 278