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

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

Neuron 1522 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: 3.6447. Min Range: -3.6447

Max Act: 3.5820. Min Act: -0.1700

Data Index: 984294 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.6134. Min Act: -0.1700

Data Index: 306231 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.6447. Min Act: -0.1700

Data Index: 590647 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5820. Min Act: -0.1700

Data Index: 767338 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5820. Min Act: -0.1700

Data Index: 778564 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5820. Min Act: -0.1700

Data Index: 172975 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.6134. Min Act: -0.1700

Data Index: 116250 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.6134. Min Act: -0.1700

Data Index: 914545 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5194. Min Act: -0.1700

Data Index: 978531 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5507. Min Act: -0.1700

Data Index: 802630 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5194. Min Act: -0.1700

Data Index: 630991 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5820. Min Act: -0.1700

Data Index: 724819 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5820. Min Act: -0.1700

Data Index: 496102 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.4881. Min Act: -0.1700

Data Index: 1111984 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5194. Min Act: -0.1700

Data Index: 502661 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5194. Min Act: -0.1700

Data Index: 800657 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.4724. Min Act: -0.1700

Data Index: 1299681 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.5194. Min Act: -0.1700

Data Index: 1316444 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.4724. Min Act: -0.1700

Data Index: 840200 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 3.6447. Min Range: -3.6447

Max Act: 3.4881. Min Act: -0.1700

Data Index: 1048286 (C4 (Web Text))

Max Activating Token Index: 483