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

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

Neuron 1469 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.7164. Min Act: -0.1700

Data Index: 1310843 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.4816. Min Act: -0.1700

Data Index: 449719 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.4972. Min Act: -0.1700

Data Index: 724962 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.4345. Min Act: -0.1700

Data Index: 1152321 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.4502. Min Act: -0.1700

Data Index: 971353 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.4345. Min Act: -0.1700

Data Index: 601358 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.4345. Min Act: -0.1700

Data Index: 1266044 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.4189. Min Act: -0.1700

Data Index: 465528 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.4032. Min Act: -0.1700

Data Index: 845341 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.3875. Min Act: -0.1700

Data Index: 620474 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.3875. Min Act: -0.1700

Data Index: 798887 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.3875. Min Act: -0.1700

Data Index: 604842 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.3561. Min Act: -0.1700

Data Index: 688384 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.3247. Min Act: -0.1700

Data Index: 604167 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.3090. Min Act: -0.1700

Data Index: 327629 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.2776. Min Act: -0.1700

Data Index: 432505 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.3090. Min Act: -0.1700

Data Index: 335298 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.2776. Min Act: -0.1700

Data Index: 1343861 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.2933. Min Act: -0.1700

Data Index: 615934 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 3.7164. Min Range: -3.7164

Max Act: 3.2619. Min Act: -0.1700

Data Index: 917182 (C4 (Web Text))

Max Activating Token Index: 674