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

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

Neuron 471 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: 4.5282. Min Range: -4.5282

Max Act: 4.5282. Min Act: -0.1700

Data Index: 457622 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.5282. Min Range: -4.5282

Max Act: 4.3095. Min Act: -0.1700

Data Index: 35867 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.5282. Min Range: -4.5282

Max Act: 4.3407. Min Act: -0.1700

Data Index: 1250819 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 4.5282. Min Range: -4.5282

Max Act: 4.2782. Min Act: -0.1700

Data Index: 726245 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 4.5282. Min Range: -4.5282

Max Act: 4.0281. Min Act: -0.1700

Data Index: 407685 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.5282. Min Range: -4.5282

Max Act: 3.9343. Min Act: -0.1700

Data Index: 612543 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.5282. Min Range: -4.5282

Max Act: 4.1219. Min Act: -0.1700

Data Index: 13743 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 4.5282. Min Range: -4.5282

Max Act: 4.0594. Min Act: -0.1700

Data Index: 428863 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 4.5282. Min Range: -4.5282

Max Act: 3.9969. Min Act: -0.1700

Data Index: 282614 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 4.5282. Min Range: -4.5282

Max Act: 4.0281. Min Act: -0.1700

Data Index: 378348 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 4.5282. Min Range: -4.5282

Max Act: 4.1219. Min Act: -0.1700

Data Index: 1242618 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 4.5282. Min Range: -4.5282

Max Act: 3.9969. Min Act: -0.1700

Data Index: 877461 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 4.5282. Min Range: -4.5282

Max Act: 3.9969. Min Act: -0.1700

Data Index: 827779 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.5282. Min Range: -4.5282

Max Act: 3.9656. Min Act: -0.1700

Data Index: 1052110 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 4.5282. Min Range: -4.5282

Max Act: 4.0281. Min Act: -0.1700

Data Index: 956416 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 4.5282. Min Range: -4.5282

Max Act: 3.9031. Min Act: -0.1700

Data Index: 544820 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 4.5282. Min Range: -4.5282

Max Act: 3.9656. Min Act: -0.1700

Data Index: 567336 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 4.5282. Min Range: -4.5282

Max Act: 4.1219. Min Act: -0.1700

Data Index: 294650 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 4.5282. Min Range: -4.5282

Max Act: 3.9656. Min Act: -0.1700

Data Index: 836718 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 4.5282. Min Range: -4.5282

Max Act: 3.9343. Min Act: -0.1700

Data Index: 85347 (C4 (Web Text))

Max Activating Token Index: 754