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

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

Neuron 1173 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.2288. Min Act: -0.1691

Data Index: 259877 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.2288. Min Act: -0.1700

Data Index: 897833 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.1976. Min Act: -0.1700

Data Index: 962636 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.1663. Min Act: -0.1700

Data Index: 544388 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.1976. Min Act: -0.1700

Data Index: 705183 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.1351. Min Act: -0.1700

Data Index: 1186692 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.1038. Min Act: -0.1700

Data Index: 673231 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.0726. Min Act: -0.1699

Data Index: 653814 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.0726. Min Act: -0.1700

Data Index: 533154 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.0726. Min Act: -0.1700

Data Index: 353587 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.0413. Min Act: -0.1699

Data Index: 144764 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.0726. Min Act: -0.1700

Data Index: 1301567 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.0413. Min Act: -0.1700

Data Index: 294156 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.0101. Min Act: -0.1700

Data Index: 1024985 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.0101. Min Act: -0.1700

Data Index: 1335188 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 5.2288. Min Range: -5.2288

Max Act: 5.0101. Min Act: -0.1700

Data Index: 215738 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 5.2288. Min Range: -5.2288

Max Act: 4.9788. Min Act: -0.1700

Data Index: 678422 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 5.2288. Min Range: -5.2288

Max Act: 4.9788. Min Act: -0.1700

Data Index: 361667 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 5.2288. Min Range: -5.2288

Max Act: 4.9788. Min Act: -0.1700

Data Index: 221039 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 5.2288. Min Range: -5.2288

Max Act: 4.9788. Min Act: -0.1700

Data Index: 431980 (C4 (Web Text))

Max Activating Token Index: 428