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

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

Neuron 1103 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: 5.1726. Min Range: -5.1726

Max Act: 4.9538. Min Act: -0.1700

Data Index: 1045553 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.9226. Min Act: -0.1700

Data Index: 315558 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 5.1726. Min Range: -5.1726

Max Act: 5.0788. Min Act: -0.1700

Data Index: 68755 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.8913. Min Act: -0.1700

Data Index: 194306 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.9851. Min Act: -0.1700

Data Index: 147614 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.9851. Min Act: -0.1700

Data Index: 1120701 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 5.1726. Min Range: -5.1726

Max Act: 5.1726. Min Act: -0.1700

Data Index: 1025395 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.8913. Min Act: -0.1700

Data Index: 833711 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.9226. Min Act: -0.1700

Data Index: 820580 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.9538. Min Act: -0.1700

Data Index: 131394 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.7351. Min Act: -0.1700

Data Index: 413986 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.8913. Min Act: -0.1700

Data Index: 488005 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 5.1726. Min Range: -5.1726

Max Act: 5.0163. Min Act: -0.1700

Data Index: 1065692 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.9538. Min Act: -0.1700

Data Index: 479764 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.8913. Min Act: -0.1700

Data Index: 1353845 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.8288. Min Act: -0.1700

Data Index: 1081450 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.6726. Min Act: -0.1700

Data Index: 287242 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.7351. Min Act: -0.1700

Data Index: 563669 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 5.1726. Min Range: -5.1726

Max Act: 4.8601. Min Act: -0.1700

Data Index: 1305930 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 5.1726. Min Range: -5.1726

Max Act: 5.0788. Min Act: -0.1700

Data Index: 602014 (C4 (Web Text))

Max Activating Token Index: 653