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

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

Neuron 1494 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1771. Min Range: -5.1771

Max Act: 5.1771. Min Act: -0.1700

Data Index: 319191 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 5.1771. Min Range: -5.1771

Max Act: 5.0521. Min Act: -0.1700

Data Index: 1311941 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.9271. Min Act: -0.1700

Data Index: 909440 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.8959. Min Act: -0.1700

Data Index: 1125035 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.8646. Min Act: -0.1700

Data Index: 348013 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.7709. Min Act: -0.1699

Data Index: 652680 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.7709. Min Act: -0.1700

Data Index: 1336502 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.8334. Min Act: -0.1700

Data Index: 524843 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.8021. Min Act: -0.1700

Data Index: 536391 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.7396. Min Act: -0.1700

Data Index: 423467 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.7396. Min Act: -0.1700

Data Index: 776410 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.7396. Min Act: -0.1700

Data Index: 580952 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.7396. Min Act: -0.1700

Data Index: 392524 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.6771. Min Act: -0.1700

Data Index: 1245051 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.7396. Min Act: -0.1700

Data Index: 144609 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.6771. Min Act: -0.1700

Data Index: 171957 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.6459. Min Act: -0.1700

Data Index: 1021403 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.7084. Min Act: -0.1700

Data Index: 795178 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.6771. Min Act: -0.1700

Data Index: 505164 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 5.1771. Min Range: -5.1771

Max Act: 4.6771. Min Act: -0.1700

Data Index: 150811 (C4 (Web Text))

Max Activating Token Index: 688