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

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

Neuron 49 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: 3.3068. Min Range: -3.3068

Max Act: 3.3068. Min Act: -0.1700

Data Index: 781501 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.3068. Min Act: -0.1700

Data Index: 849948 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2754. Min Act: -0.1700

Data Index: 1252684 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2754. Min Act: -0.1700

Data Index: 252994 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2439. Min Act: -0.1700

Data Index: 430406 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2439. Min Act: -0.1700

Data Index: 169718 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.1968. Min Act: -0.1700

Data Index: 757420 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2282. Min Act: -0.1700

Data Index: 462875 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.1810. Min Act: -0.1700

Data Index: 515040 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2282. Min Act: -0.1700

Data Index: 391116 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2125. Min Act: -0.1700

Data Index: 1042273 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.1968. Min Act: -0.1700

Data Index: 403795 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2125. Min Act: -0.1700

Data Index: 1034746 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2282. Min Act: -0.1700

Data Index: 201533 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.1810. Min Act: -0.1700

Data Index: 354913 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2125. Min Act: -0.1700

Data Index: 959110 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.1810. Min Act: -0.1700

Data Index: 530810 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.1968. Min Act: -0.1700

Data Index: 439460 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.1653. Min Act: -0.1700

Data Index: 363268 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.1653. Min Act: -0.1700

Data Index: 587260 (C4 (Web Text))

Max Activating Token Index: 330