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

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

Neuron 993 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.5527. Min Act: -0.1700

Data Index: 461920 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.5057. Min Act: -0.1700

Data Index: 208738 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.4116. Min Act: -0.1700

Data Index: 130353 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3959. Min Act: -0.1700

Data Index: 665364 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.4116. Min Act: -0.1700

Data Index: 1125906 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3959. Min Act: -0.1700

Data Index: 1024668 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3646. Min Act: -0.1700

Data Index: 591534 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.4116. Min Act: -0.1700

Data Index: 1008413 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3332. Min Act: -0.1700

Data Index: 87437 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3175. Min Act: -0.1700

Data Index: 1193147 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3646. Min Act: -0.1700

Data Index: 108807 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3646. Min Act: -0.1700

Data Index: 1172941 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3489. Min Act: -0.1700

Data Index: 770956 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3175. Min Act: -0.1700

Data Index: 1167788 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3646. Min Act: -0.1700

Data Index: 37705 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3803. Min Act: -0.1700

Data Index: 894836 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3646. Min Act: -0.1700

Data Index: 999423 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3803. Min Act: -0.1700

Data Index: 258311 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3018. Min Act: -0.1700

Data Index: 185766 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 3.5527. Min Range: -3.5527

Max Act: 3.3175. Min Act: -0.1700

Data Index: 1003152 (C4 (Web Text))

Max Activating Token Index: 704