Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1317 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.6568. Min Act: -0.1700

Data Index: 1106637 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.6100. Min Act: -0.1700

Data Index: 1288317 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.5475. Min Act: -0.1700

Data Index: 487017 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.5631. Min Act: -0.1700

Data Index: 896611 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.4693. Min Act: -0.1700

Data Index: 53647 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.3756. Min Act: -0.1700

Data Index: 1439767 (Python Code)

Max Activating Token Index: 913

Text #6

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.4381. Min Act: -0.1700

Data Index: 946055 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.3287. Min Act: -0.1700

Data Index: 317552 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.3443. Min Act: -0.1700

Data Index: 500002 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.3600. Min Act: -0.1700

Data Index: 1229587 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.3287. Min Act: -0.1700

Data Index: 59024 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.2662. Min Act: -0.1700

Data Index: 791695 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.2818. Min Act: -0.1700

Data Index: 378934 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.2662. Min Act: -0.1700

Data Index: 1232274 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.3287. Min Act: -0.1700

Data Index: 930164 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.2974. Min Act: -0.1700

Data Index: 18332 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.3287. Min Act: -0.1700

Data Index: 187620 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.2974. Min Act: -0.1700

Data Index: 1305879 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.2818. Min Act: -0.1700

Data Index: 189182 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 5.6568. Min Range: -5.6568

Max Act: 5.2506. Min Act: -0.1700

Data Index: 15612 (C4 (Web Text))

Max Activating Token Index: 278