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

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

Neuron 904 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.2443. Min Act: -0.1700

Data Index: 753678 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.1656. Min Act: -0.1700

Data Index: 592152 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.1656. Min Act: -0.1700

Data Index: 417744 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.1499. Min Act: -0.1700

Data Index: 1399666 (Python Code)

Max Activating Token Index: 363

Text #4

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.1499. Min Act: -0.1700

Data Index: 657166 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.1499. Min Act: -0.1700

Data Index: 569133 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.1184. Min Act: -0.1700

Data Index: 996071 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.1026. Min Act: -0.1700

Data Index: 95471 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.1026. Min Act: -0.1700

Data Index: 1276966 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.0868. Min Act: -0.1700

Data Index: 543327 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.0395. Min Act: -0.1700

Data Index: 215829 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.0868. Min Act: -0.1700

Data Index: 472581 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.0711. Min Act: -0.1700

Data Index: 1039750 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.0553. Min Act: -0.1700

Data Index: 701014 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.0553. Min Act: -0.1700

Data Index: 431711 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.0395. Min Act: -0.1700

Data Index: 484242 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.0237. Min Act: -0.1700

Data Index: 439602 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.0237. Min Act: -0.1700

Data Index: 418732 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.0395. Min Act: -0.1700

Data Index: 36306 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 3.2443. Min Range: -3.2443

Max Act: 3.0079. Min Act: -0.1700

Data Index: 483189 (C4 (Web Text))

Max Activating Token Index: 912