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

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

Neuron 1485 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: 3.8549. Min Range: -3.8549

Max Act: 3.8549. Min Act: -0.1700

Data Index: 131268 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.8236. Min Act: -0.1700

Data Index: 1115811 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.8236. Min Act: -0.1700

Data Index: 101732 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.8236. Min Act: -0.1700

Data Index: 362642 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.7924. Min Act: -0.1700

Data Index: 802733 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.7924. Min Act: -0.1700

Data Index: 558361 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.7611. Min Act: -0.1700

Data Index: 891229 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.7611. Min Act: -0.1700

Data Index: 1293844 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.6985. Min Act: -0.1700

Data Index: 1321182 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.7611. Min Act: -0.1700

Data Index: 236668 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.7611. Min Act: -0.1700

Data Index: 283015 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.7298. Min Act: -0.1700

Data Index: 657120 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.6985. Min Act: -0.1700

Data Index: 525481 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.7298. Min Act: -0.1700

Data Index: 365591 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.6985. Min Act: -0.1700

Data Index: 853867 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.7298. Min Act: -0.1700

Data Index: 296796 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.6985. Min Act: -0.1700

Data Index: 961422 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.6985. Min Act: -0.1700

Data Index: 1038780 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.6985. Min Act: -0.1700

Data Index: 1093018 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 3.8549. Min Range: -3.8549

Max Act: 3.6985. Min Act: -0.1700

Data Index: 619573 (C4 (Web Text))

Max Activating Token Index: 19