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

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

Neuron 298 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: 3.9595. Min Range: -3.9595

Max Act: 3.9595. Min Act: -0.1700

Data Index: 1355184 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.9282. Min Act: -0.1700

Data Index: 760917 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.8970. Min Act: -0.1700

Data Index: 695069 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.9595. Min Act: -0.1700

Data Index: 314928 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.8970. Min Act: -0.1700

Data Index: 1087984 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.8970. Min Act: -0.1700

Data Index: 547057 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.8970. Min Act: -0.1700

Data Index: 812289 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.8657. Min Act: -0.1700

Data Index: 486191 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.8657. Min Act: -0.1700

Data Index: 916789 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.8657. Min Act: -0.1700

Data Index: 897415 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.8031. Min Act: -0.1700

Data Index: 49490 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.8031. Min Act: -0.1700

Data Index: 550541 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.8344. Min Act: -0.1700

Data Index: 979067 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.8031. Min Act: -0.1700

Data Index: 900314 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.7718. Min Act: -0.1700

Data Index: 92216 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.7406. Min Act: -0.1700

Data Index: 1265214 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.7718. Min Act: -0.1700

Data Index: 976297 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.7718. Min Act: -0.1700

Data Index: 455924 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.7406. Min Act: -0.1700

Data Index: 912616 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 3.9595. Min Range: -3.9595

Max Act: 3.7718. Min Act: -0.1700

Data Index: 160698 (C4 (Web Text))

Max Activating Token Index: 317