Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 48 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.8549. Min Act: -0.1700

Data Index: 742104 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.6987. Min Act: -0.1700

Data Index: 591127 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.7299. Min Act: -0.1700

Data Index: 1357482 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.6049. Min Act: -0.1700

Data Index: 1205265 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.6362. Min Act: -0.1700

Data Index: 136411 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.5737. Min Act: -0.1700

Data Index: 215773 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.6049. Min Act: -0.1700

Data Index: 161224 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.5737. Min Act: -0.1699

Data Index: 30841 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.5424. Min Act: -0.1700

Data Index: 472638 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.5424. Min Act: -0.1700

Data Index: 137499 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.5737. Min Act: -0.1700

Data Index: 966525 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.5737. Min Act: -0.1700

Data Index: 573427 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.5737. Min Act: -0.1700

Data Index: 805464 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.4955. Min Act: -0.1700

Data Index: 348310 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.5737. Min Act: -0.1700

Data Index: 1290597 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.5424. Min Act: -0.1700

Data Index: 431313 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.5424. Min Act: -0.1700

Data Index: 1001233 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.5112. Min Act: -0.1700

Data Index: 981672 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.4955. Min Act: -0.1700

Data Index: 631469 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 4.8549. Min Range: -4.8549

Max Act: 4.5424. Min Act: -0.1700

Data Index: 1015542 (C4 (Web Text))

Max Activating Token Index: 117