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

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

Neuron 219 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.9313. Min Act: -0.1700

Data Index: 1387143 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.7436. Min Act: -0.1700

Data Index: 1413067 (Python Code)

Max Activating Token Index: 304

Text #2

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.6341. Min Act: -0.1700

Data Index: 1628431 (Python Code)

Max Activating Token Index: 701

Text #3

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.6184. Min Act: -0.1700

Data Index: 1466750 (Python Code)

Max Activating Token Index: 369

Text #4

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5714. Min Act: -0.1700

Data Index: 1061582 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5558. Min Act: -0.1700

Data Index: 614780 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5714. Min Act: -0.1700

Data Index: 1528664 (Python Code)

Max Activating Token Index: 787

Text #7

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5401. Min Act: -0.1700

Data Index: 1525640 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5245. Min Act: -0.1700

Data Index: 538519 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5558. Min Act: -0.1700

Data Index: 532786 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5714. Min Act: -0.1700

Data Index: 675064 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5714. Min Act: -0.1700

Data Index: 277344 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5245. Min Act: -0.1700

Data Index: 1411331 (Python Code)

Max Activating Token Index: 512

Text #13

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5714. Min Act: -0.1700

Data Index: 461254 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5088. Min Act: -0.1700

Data Index: 404219 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5558. Min Act: -0.1700

Data Index: 993617 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5714. Min Act: -0.1700

Data Index: 572779 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5088. Min Act: -0.1700

Data Index: 1360477 (Python Code)

Max Activating Token Index: 292

Text #18

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5088. Min Act: -0.1700

Data Index: 1643929 (Python Code)

Max Activating Token Index: 929

Text #19

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.5401. Min Act: -0.1700

Data Index: 1451182 (Python Code)

Max Activating Token Index: 229