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

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

Neuron 1251 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.5448. Min Act: -0.1700

Data Index: 457899 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.4195. Min Act: -0.1700

Data Index: 445789 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.4508. Min Act: -0.1700

Data Index: 284010 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.4822. Min Act: -0.1700

Data Index: 1172380 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.3881. Min Act: -0.1700

Data Index: 651602 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.4195. Min Act: -0.1700

Data Index: 854688 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.3567. Min Act: -0.1700

Data Index: 141481 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.3567. Min Act: -0.1700

Data Index: 780918 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.3253. Min Act: -0.1700

Data Index: 708428 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.2782. Min Act: -0.1700

Data Index: 397371 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.2468. Min Act: -0.1700

Data Index: 1164604 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.3567. Min Act: -0.1700

Data Index: 1340841 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.2310. Min Act: -0.1700

Data Index: 1188825 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.2625. Min Act: -0.1700

Data Index: 1049156 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.2939. Min Act: -0.1700

Data Index: 1124685 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.2939. Min Act: -0.1700

Data Index: 221733 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.2939. Min Act: -0.1700

Data Index: 725170 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.2468. Min Act: -0.1700

Data Index: 725422 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.2153. Min Act: -0.1700

Data Index: 1342083 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 3.5448. Min Range: -3.5448

Max Act: 3.2468. Min Act: -0.1700

Data Index: 457924 (C4 (Web Text))

Max Activating Token Index: 798