Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 549 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.4395. Min Act: -0.1700

Data Index: 1507531 (Python Code)

Max Activating Token Index: 277

Text #1

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.4395. Min Act: -0.1700

Data Index: 1091251 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.4395. Min Act: -0.1700

Data Index: 1010274 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.4081. Min Act: -0.1700

Data Index: 15240 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.4238. Min Act: -0.1700

Data Index: 1525227 (Python Code)

Max Activating Token Index: 398

Text #5

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.4395. Min Act: -0.1700

Data Index: 779993 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.4238. Min Act: -0.1700

Data Index: 749922 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.4395. Min Act: -0.1700

Data Index: 825724 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3924. Min Act: -0.1700

Data Index: 956420 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.4238. Min Act: -0.1700

Data Index: 13827 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.4081. Min Act: -0.1700

Data Index: 1155764 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3924. Min Act: -0.1700

Data Index: 1542034 (Python Code)

Max Activating Token Index: 389

Text #12

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3924. Min Act: -0.1700

Data Index: 1220915 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3768. Min Act: -0.1700

Data Index: 205812 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3768. Min Act: -0.1700

Data Index: 679267 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3768. Min Act: -0.1700

Data Index: 1493773 (Python Code)

Max Activating Token Index: 144

Text #16

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3611. Min Act: -0.1700

Data Index: 166457 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3611. Min Act: -0.1700

Data Index: 68445 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3611. Min Act: -0.1700

Data Index: 1564992 (Python Code)

Max Activating Token Index: 640

Text #19

Max Range: 3.4395. Min Range: -3.4395

Max Act: 3.3611. Min Act: -0.1700

Data Index: 10935 (C4 (Web Text))

Max Activating Token Index: 963