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

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

Neuron 1697 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: 5.3193. Min Range: -5.3193

Max Act: 5.3193. Min Act: -0.1700

Data Index: 91536 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.3193. Min Act: -0.1700

Data Index: 192852 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.1006. Min Act: -0.1700

Data Index: 588938 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.2256. Min Act: -0.1700

Data Index: 447960 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.1943. Min Act: -0.1700

Data Index: 860071 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.1318. Min Act: -0.1700

Data Index: 711877 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.1318. Min Act: -0.1700

Data Index: 629063 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.0693. Min Act: -0.1700

Data Index: 970558 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.0693. Min Act: -0.1700

Data Index: 724830 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.0381. Min Act: -0.1700

Data Index: 485331 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9443. Min Act: -0.1700

Data Index: 415040 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9443. Min Act: -0.1700

Data Index: 686001 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9131. Min Act: -0.1700

Data Index: 563302 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9756. Min Act: -0.1700

Data Index: 681793 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9131. Min Act: -0.1700

Data Index: 712748 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.8818. Min Act: -0.1700

Data Index: 991971 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9756. Min Act: -0.1700

Data Index: 1114974 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9131. Min Act: -0.1700

Data Index: 550979 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9443. Min Act: -0.1700

Data Index: 282002 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9131. Min Act: -0.1700

Data Index: 352298 (C4 (Web Text))

Max Activating Token Index: 394