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

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

Neuron 386 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.8513. Min Act: -0.1700

Data Index: 513398 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.7574. Min Act: -0.1700

Data Index: 570758 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.7887. Min Act: -0.1700

Data Index: 1137145 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.7261. Min Act: -0.1700

Data Index: 121687 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.7261. Min Act: -0.1700

Data Index: 740515 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.7261. Min Act: -0.1700

Data Index: 615394 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.7105. Min Act: -0.1700

Data Index: 535995 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.7261. Min Act: -0.1700

Data Index: 654174 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.7261. Min Act: -0.1700

Data Index: 871962 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.6948. Min Act: -0.1700

Data Index: 374551 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.7105. Min Act: -0.1700

Data Index: 1034444 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.7105. Min Act: -0.1700

Data Index: 359990 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.6948. Min Act: -0.1700

Data Index: 611262 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.6792. Min Act: -0.1700

Data Index: 875617 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.6948. Min Act: -0.1700

Data Index: 989420 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.6948. Min Act: -0.1700

Data Index: 269584 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.6948. Min Act: -0.1700

Data Index: 1267547 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.6948. Min Act: -0.1700

Data Index: 132628 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.6322. Min Act: -0.1700

Data Index: 688919 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 3.8513. Min Range: -3.8513

Max Act: 3.6635. Min Act: -0.1700

Data Index: 171292 (C4 (Web Text))

Max Activating Token Index: 497