Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1528 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.8354. Min Act: -0.1700

Data Index: 647506 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.8354. Min Act: -0.1700

Data Index: 646827 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.7415. Min Act: -0.1700

Data Index: 933647 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.6633. Min Act: -0.1700

Data Index: 644499 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.6476. Min Act: -0.1700

Data Index: 1067422 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.6320. Min Act: -0.1700

Data Index: 1347885 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.6476. Min Act: -0.1700

Data Index: 15649 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.6163. Min Act: -0.1700

Data Index: 811805 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.6320. Min Act: -0.1700

Data Index: 332168 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.5694. Min Act: -0.1700

Data Index: 562635 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.5694. Min Act: -0.1700

Data Index: 1298949 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.5537. Min Act: -0.1700

Data Index: 945270 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.5694. Min Act: -0.1700

Data Index: 457387 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.5224. Min Act: -0.1700

Data Index: 508924 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.5224. Min Act: -0.1700

Data Index: 177999 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.5067. Min Act: -0.1700

Data Index: 1076141 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.5067. Min Act: -0.1700

Data Index: 850393 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.4910. Min Act: -0.1700

Data Index: 828662 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.4910. Min Act: -0.1700

Data Index: 192010 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 3.8354. Min Range: -3.8354

Max Act: 3.4597. Min Act: -0.1700

Data Index: 670981 (C4 (Web Text))

Max Activating Token Index: 848