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

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

Neuron 1146 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: 3.5124. Min Range: -3.5124

Max Act: 3.5124. Min Act: -0.1700

Data Index: 519798 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.3556. Min Act: -0.1700

Data Index: 1159611 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.4183. Min Act: -0.1700

Data Index: 94414 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.3870. Min Act: -0.1700

Data Index: 843640 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.4183. Min Act: -0.1700

Data Index: 729014 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.3556. Min Act: -0.1700

Data Index: 1190081 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.2928. Min Act: -0.1700

Data Index: 822105 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.2299. Min Act: -0.1700

Data Index: 803571 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.1670. Min Act: -0.1700

Data Index: 422377 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.1985. Min Act: -0.1700

Data Index: 414851 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.2928. Min Act: -0.1700

Data Index: 966513 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.2299. Min Act: -0.1700

Data Index: 1328407 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.2299. Min Act: -0.1700

Data Index: 662943 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.2614. Min Act: -0.1700

Data Index: 397505 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.1985. Min Act: -0.1700

Data Index: 748842 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.2928. Min Act: -0.1700

Data Index: 314011 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.2614. Min Act: -0.1700

Data Index: 411824 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.1985. Min Act: -0.1700

Data Index: 93570 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.1985. Min Act: -0.1700

Data Index: 521029 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 3.5124. Min Range: -3.5124

Max Act: 3.1985. Min Act: -0.1700

Data Index: 38034 (C4 (Web Text))

Max Activating Token Index: 495