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

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

Neuron 762 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: 3.3400. Min Range: -3.3400

Max Act: 3.3400. Min Act: -0.1700

Data Index: 498317 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.2772. Min Act: -0.1700

Data Index: 1170344 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.2143. Min Act: -0.1700

Data Index: 589211 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.1356. Min Act: -0.1700

Data Index: 842941 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.1041. Min Act: -0.1700

Data Index: 198088 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.1513. Min Act: -0.1700

Data Index: 827615 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.0883. Min Act: -0.1700

Data Index: 42221 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.0410. Min Act: -0.1700

Data Index: 1054242 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9302. Min Act: -0.1700

Data Index: 889614 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9936. Min Act: -0.1700

Data Index: 876752 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9936. Min Act: -0.1700

Data Index: 624546 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9619. Min Act: -0.1700

Data Index: 263814 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9777. Min Act: -0.1700

Data Index: 548934 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.0094. Min Act: -0.1700

Data Index: 99064 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 3.3400. Min Range: -3.3400

Max Act: 3.0252. Min Act: -0.1700

Data Index: 158106 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9777. Min Act: -0.1700

Data Index: 971112 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9777. Min Act: -0.1700

Data Index: 1211743 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9777. Min Act: -0.1700

Data Index: 1124673 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9302. Min Act: -0.1700

Data Index: 477798 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 3.3400. Min Range: -3.3400

Max Act: 2.9936. Min Act: -0.1700

Data Index: 1086613 (C4 (Web Text))

Max Activating Token Index: 782