Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1603 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.5432. Min Act: -0.1700

Data Index: 1350079 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.5432. Min Act: -0.1700

Data Index: 1274424 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.5432. Min Act: -0.1700

Data Index: 412336 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.5119. Min Act: -0.1700

Data Index: 695329 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.5276. Min Act: -0.1700

Data Index: 779540 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.5119. Min Act: -0.1700

Data Index: 1290930 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.5276. Min Act: -0.1700

Data Index: 389297 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.4806. Min Act: -0.1700

Data Index: 565576 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.4806. Min Act: -0.1700

Data Index: 963399 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.4492. Min Act: -0.1700

Data Index: 199570 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.4962. Min Act: -0.1700

Data Index: 423639 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.4649. Min Act: -0.1700

Data Index: 45323 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.4649. Min Act: -0.1700

Data Index: 555896 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.4335. Min Act: -0.1700

Data Index: 643348 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.4649. Min Act: -0.1700

Data Index: 882254 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.4649. Min Act: -0.1700

Data Index: 623313 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.4492. Min Act: -0.1700

Data Index: 57780 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.4492. Min Act: -0.1700

Data Index: 976580 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.4649. Min Act: -0.1700

Data Index: 1256554 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 3.5432. Min Range: -3.5432

Max Act: 3.4335. Min Act: -0.1700

Data Index: 920527 (C4 (Web Text))

Max Activating Token Index: 579