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

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

Neuron 1186 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: 3.9268. Min Range: -3.9268

Max Act: 3.9268. Min Act: -0.1700

Data Index: 915829 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.8643. Min Act: -0.1700

Data Index: 542212 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.8330. Min Act: -0.1700

Data Index: 62528 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.8017. Min Act: -0.1700

Data Index: 514794 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.8017. Min Act: -0.1700

Data Index: 297207 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.8017. Min Act: -0.1700

Data Index: 177555 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.8017. Min Act: -0.1700

Data Index: 1124223 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7704. Min Act: -0.1700

Data Index: 310496 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7391. Min Act: -0.1700

Data Index: 36388 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7704. Min Act: -0.1700

Data Index: 996552 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7704. Min Act: -0.1700

Data Index: 816447 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7704. Min Act: -0.1700

Data Index: 1262220 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7078. Min Act: -0.1700

Data Index: 343118 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7704. Min Act: -0.1700

Data Index: 27762 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7704. Min Act: -0.1700

Data Index: 138049 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7704. Min Act: -0.1700

Data Index: 142960 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7391. Min Act: -0.1700

Data Index: 1000652 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7391. Min Act: -0.1700

Data Index: 1032038 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7078. Min Act: -0.1700

Data Index: 495824 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7391. Min Act: -0.1700

Data Index: 698372 (C4 (Web Text))

Max Activating Token Index: 540