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

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

Neuron 1376 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: 3.7568. Min Range: -3.7568

Max Act: 3.7568. Min Act: -0.1700

Data Index: 403316 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.7099. Min Act: -0.1700

Data Index: 1293738 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.7412. Min Act: -0.1700

Data Index: 1183908 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.6786. Min Act: -0.1700

Data Index: 346809 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.6786. Min Act: -0.1700

Data Index: 85893 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.6786. Min Act: -0.1700

Data Index: 253793 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.6786. Min Act: -0.1700

Data Index: 54902 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.6473. Min Act: -0.1700

Data Index: 89360 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.6316. Min Act: -0.1700

Data Index: 28527 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.6316. Min Act: -0.1700

Data Index: 1147522 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.6473. Min Act: -0.1700

Data Index: 1083288 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.6316. Min Act: -0.1700

Data Index: 747387 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.6160. Min Act: -0.1700

Data Index: 583145 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.6003. Min Act: -0.1700

Data Index: 767991 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.6003. Min Act: -0.1700

Data Index: 1180605 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.5847. Min Act: -0.1700

Data Index: 1320203 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.5847. Min Act: -0.1700

Data Index: 1131862 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.5847. Min Act: -0.1700

Data Index: 1053878 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.5847. Min Act: -0.1700

Data Index: 151935 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 3.7568. Min Range: -3.7568

Max Act: 3.5847. Min Act: -0.1700

Data Index: 964457 (C4 (Web Text))

Max Activating Token Index: 644