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

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

Neuron 1263 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.7417. Min Act: -0.1700

Data Index: 195786 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.6791. Min Act: -0.1700

Data Index: 838999 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.6634. Min Act: -0.1700

Data Index: 701485 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.6321. Min Act: -0.1700

Data Index: 717292 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.6008. Min Act: -0.1700

Data Index: 1217641 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.5539. Min Act: -0.1700

Data Index: 576357 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.4912. Min Act: -0.1700

Data Index: 77230 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.5382. Min Act: -0.1700

Data Index: 484390 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.5695. Min Act: -0.1700

Data Index: 358051 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.5382. Min Act: -0.1700

Data Index: 1237116 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.5539. Min Act: -0.1700

Data Index: 312425 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.4755. Min Act: -0.1700

Data Index: 9914 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.4912. Min Act: -0.1700

Data Index: 75771 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.5225. Min Act: -0.1700

Data Index: 1046362 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.4598. Min Act: -0.1700

Data Index: 569703 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.4912. Min Act: -0.1700

Data Index: 11890 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.4755. Min Act: -0.1700

Data Index: 1358711 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.4912. Min Act: -0.1700

Data Index: 919598 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.5225. Min Act: -0.1700

Data Index: 339877 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 3.7417. Min Range: -3.7417

Max Act: 3.4755. Min Act: -0.1700

Data Index: 551636 (C4 (Web Text))

Max Activating Token Index: 246