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

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

Neuron 1204 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.7708. Min Act: -0.1700

Data Index: 722235 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.7708. Min Act: -0.1700

Data Index: 334270 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.6769. Min Act: -0.1700

Data Index: 193807 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.7082. Min Act: -0.1700

Data Index: 209991 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.6613. Min Act: -0.1700

Data Index: 518793 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.6613. Min Act: -0.1700

Data Index: 656386 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.6769. Min Act: -0.1700

Data Index: 1052741 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5674. Min Act: -0.1700

Data Index: 1048942 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.6143. Min Act: -0.1700

Data Index: 600521 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5204. Min Act: -0.1700

Data Index: 999190 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5517. Min Act: -0.1700

Data Index: 1016480 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5674. Min Act: -0.1700

Data Index: 153029 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5830. Min Act: -0.1700

Data Index: 697563 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.6143. Min Act: -0.1700

Data Index: 179515 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5047. Min Act: -0.1700

Data Index: 185567 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5047. Min Act: -0.1700

Data Index: 1007214 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.4734. Min Act: -0.1700

Data Index: 691291 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5204. Min Act: -0.1700

Data Index: 811371 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.4890. Min Act: -0.1700

Data Index: 1066511 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5204. Min Act: -0.1700

Data Index: 702815 (C4 (Web Text))

Max Activating Token Index: 882