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

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

Neuron 103 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: 3.7110. Min Range: -3.7110

Max Act: 3.7110. Min Act: -0.1700

Data Index: 440233 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.5544. Min Act: -0.1700

Data Index: 381015 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.5544. Min Act: -0.1700

Data Index: 727700 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.5231. Min Act: -0.1700

Data Index: 219494 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.5544. Min Act: -0.1700

Data Index: 1355260 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4918. Min Act: -0.1700

Data Index: 1057165 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4918. Min Act: -0.1700

Data Index: 550690 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4604. Min Act: -0.1700

Data Index: 708329 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4291. Min Act: -0.1700

Data Index: 757977 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.3977. Min Act: -0.1700

Data Index: 941313 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.3977. Min Act: -0.1700

Data Index: 901138 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.3977. Min Act: -0.1700

Data Index: 934538 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.3977. Min Act: -0.1700

Data Index: 495414 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.3977. Min Act: -0.1700

Data Index: 1022128 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.3977. Min Act: -0.1700

Data Index: 897452 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.3663. Min Act: -0.1700

Data Index: 527721 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.3663. Min Act: -0.1700

Data Index: 937585 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.3663. Min Act: -0.1700

Data Index: 798708 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.3663. Min Act: -0.1700

Data Index: 596929 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.3663. Min Act: -0.1700

Data Index: 993919 (C4 (Web Text))

Max Activating Token Index: 114