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

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

Neuron 175 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2768. Min Act: -0.1700

Data Index: 988001 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2611. Min Act: -0.1700

Data Index: 591028 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2611. Min Act: -0.1700

Data Index: 79109 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2296. Min Act: -0.1700

Data Index: 544385 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2611. Min Act: -0.1700

Data Index: 138597 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2611. Min Act: -0.1700

Data Index: 1156312 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2453. Min Act: -0.1700

Data Index: 753529 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2453. Min Act: -0.1700

Data Index: 1321297 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2453. Min Act: -0.1700

Data Index: 525995 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2296. Min Act: -0.1700

Data Index: 934179 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2453. Min Act: -0.1700

Data Index: 970869 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2453. Min Act: -0.1700

Data Index: 633327 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2296. Min Act: -0.1700

Data Index: 1202650 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2296. Min Act: -0.1700

Data Index: 1182907 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2296. Min Act: -0.1700

Data Index: 336273 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2296. Min Act: -0.1700

Data Index: 586474 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2453. Min Act: -0.1700

Data Index: 1048576 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2296. Min Act: -0.1700

Data Index: 999271 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.2139. Min Act: -0.1700

Data Index: 592838 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 3.2768. Min Range: -3.2768

Max Act: 3.1982. Min Act: -0.1700

Data Index: 1031923 (C4 (Web Text))

Max Activating Token Index: 21