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

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

Neuron 1299 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: 3.5192. Min Range: -3.5192

Max Act: 3.5192. Min Act: -0.1700

Data Index: 1392591 (Python Code)

Max Activating Token Index: 774

Text #1

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4879. Min Act: -0.1700

Data Index: 400196 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4722. Min Act: -0.1700

Data Index: 314303 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4566. Min Act: -0.1700

Data Index: 771611 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4722. Min Act: -0.1700

Data Index: 1422942 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1390923 (Python Code)

Max Activating Token Index: 344

Text #6

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4722. Min Act: -0.1700

Data Index: 694274 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4722. Min Act: -0.1700

Data Index: 238541 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4879. Min Act: -0.1700

Data Index: 155934 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4409. Min Act: -0.1700

Data Index: 50159 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1553128 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1597384 (Python Code)

Max Activating Token Index: 363

Text #12

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1166692 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4409. Min Act: -0.1700

Data Index: 517731 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4409. Min Act: -0.1700

Data Index: 637907 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4566. Min Act: -0.1700

Data Index: 344971 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4566. Min Act: -0.1700

Data Index: 476251 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4409. Min Act: -0.1700

Data Index: 1495007 (Python Code)

Max Activating Token Index: 520

Text #18

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4409. Min Act: -0.1700

Data Index: 1490142 (Python Code)

Max Activating Token Index: 768

Text #19

Max Range: 3.5192. Min Range: -3.5192

Max Act: 3.4409. Min Act: -0.1700

Data Index: 1373002 (Python Code)

Max Activating Token Index: 243