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

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

Neuron 512 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: 3.6995. Min Range: -3.6995

Max Act: 3.6995. Min Act: -0.1700

Data Index: 898780 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.6682. Min Act: -0.1700

Data Index: 50301 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.6369. Min Act: -0.1700

Data Index: 357323 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.6682. Min Act: -0.1700

Data Index: 1016818 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.6212. Min Act: -0.1700

Data Index: 488180 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.6212. Min Act: -0.1700

Data Index: 791975 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5899. Min Act: -0.1700

Data Index: 594438 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5899. Min Act: -0.1700

Data Index: 630825 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5743. Min Act: -0.1700

Data Index: 703237 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5899. Min Act: -0.1700

Data Index: 780982 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5273. Min Act: -0.1700

Data Index: 1177228 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5899. Min Act: -0.1700

Data Index: 94850 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5743. Min Act: -0.1700

Data Index: 905680 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5743. Min Act: -0.1700

Data Index: 576064 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5273. Min Act: -0.1700

Data Index: 643196 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5586. Min Act: -0.1700

Data Index: 137858 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5899. Min Act: -0.1700

Data Index: 612758 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5429. Min Act: -0.1700

Data Index: 433929 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5586. Min Act: -0.1700

Data Index: 820640 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 3.6995. Min Range: -3.6995

Max Act: 3.5743. Min Act: -0.1700

Data Index: 648170 (C4 (Web Text))

Max Activating Token Index: 686