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

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

Neuron 785 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.4543. Min Act: -0.1700

Data Index: 203417 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.2668. Min Act: -0.1700

Data Index: 769757 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.2355. Min Act: -0.1700

Data Index: 1178641 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.2355. Min Act: -0.1700

Data Index: 450684 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.2355. Min Act: -0.1700

Data Index: 281410 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.2043. Min Act: -0.1700

Data Index: 1356538 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.1730. Min Act: -0.1700

Data Index: 1283507 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.1730. Min Act: -0.1700

Data Index: 1117018 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.1105. Min Act: -0.1700

Data Index: 683517 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.1730. Min Act: -0.1700

Data Index: 185780 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.1418. Min Act: -0.1700

Data Index: 428430 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.1105. Min Act: -0.1700

Data Index: 455953 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.0793. Min Act: -0.1700

Data Index: 424369 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.1105. Min Act: -0.1700

Data Index: 702873 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.0793. Min Act: -0.1700

Data Index: 364726 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.0793. Min Act: -0.1700

Data Index: 143393 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.0793. Min Act: -0.1700

Data Index: 29546 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.0793. Min Act: -0.1700

Data Index: 1121322 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.0793. Min Act: -0.1700

Data Index: 755939 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 5.4543. Min Range: -5.4543

Max Act: 5.0793. Min Act: -0.1700

Data Index: 444068 (C4 (Web Text))

Max Activating Token Index: 548