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

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

Neuron 621 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.6437. Min Act: -0.1700

Data Index: 647378 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.5500. Min Act: -0.1700

Data Index: 579686 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.5500. Min Act: -0.1700

Data Index: 778168 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.5500. Min Act: -0.1700

Data Index: 523594 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.4250. Min Act: -0.1700

Data Index: 221432 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3937. Min Act: -0.1700

Data Index: 229234 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.4250. Min Act: -0.1700

Data Index: 1282325 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3312. Min Act: -0.1700

Data Index: 1026555 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3937. Min Act: -0.1700

Data Index: 487818 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3937. Min Act: -0.1700

Data Index: 44086 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3625. Min Act: -0.1700

Data Index: 151990 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3625. Min Act: -0.1700

Data Index: 1346272 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3312. Min Act: -0.1700

Data Index: 212177 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3625. Min Act: -0.1700

Data Index: 521668 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3625. Min Act: -0.1700

Data Index: 323858 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3000. Min Act: -0.1700

Data Index: 1008480 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3312. Min Act: -0.1700

Data Index: 1050755 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3312. Min Act: -0.1700

Data Index: 61196 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3000. Min Act: -0.1700

Data Index: 924943 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.3000. Min Act: -0.1700

Data Index: 1198543 (C4 (Web Text))

Max Activating Token Index: 780