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

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

Neuron 1273 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1540. Min Range: -4.1540

Max Act: 4.1540. Min Act: -0.1700

Data Index: 271713 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 4.1540. Min Range: -4.1540

Max Act: 4.0289. Min Act: -0.1700

Data Index: 437572 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.9977. Min Act: -0.1700

Data Index: 538741 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.9039. Min Act: -0.1700

Data Index: 571047 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.8100. Min Act: -0.1700

Data Index: 806882 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.7787. Min Act: -0.1700

Data Index: 289512 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.7787. Min Act: -0.1700

Data Index: 737185 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.7475. Min Act: -0.1700

Data Index: 342424 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.6849. Min Act: -0.1700

Data Index: 1173899 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.6849. Min Act: -0.1700

Data Index: 774335 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.6223. Min Act: -0.1700

Data Index: 1046041 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.6223. Min Act: -0.1700

Data Index: 1265880 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.6223. Min Act: -0.1700

Data Index: 361479 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.6066. Min Act: -0.1700

Data Index: 599986 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.5910. Min Act: -0.1700

Data Index: 396949 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.5910. Min Act: -0.1700

Data Index: 209775 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.5753. Min Act: -0.1700

Data Index: 493876 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.5596. Min Act: -0.1700

Data Index: 1174525 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.5596. Min Act: -0.1700

Data Index: 645005 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 4.1540. Min Range: -4.1540

Max Act: 3.5910. Min Act: -0.1700

Data Index: 43527 (C4 (Web Text))

Max Activating Token Index: 806