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

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

Neuron 693 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.9252. Min Act: -0.1700

Data Index: 883183 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.8002. Min Act: -0.1700

Data Index: 48691 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.8002. Min Act: -0.1700

Data Index: 953317 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.8314. Min Act: -0.1700

Data Index: 325825 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.8002. Min Act: -0.1700

Data Index: 1295108 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.8002. Min Act: -0.1700

Data Index: 549447 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.8002. Min Act: -0.1700

Data Index: 767660 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.7377. Min Act: -0.1700

Data Index: 797779 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.7689. Min Act: -0.1700

Data Index: 1220821 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.7377. Min Act: -0.1700

Data Index: 823159 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.7377. Min Act: -0.1700

Data Index: 377176 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.7377. Min Act: -0.1700

Data Index: 1332450 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.6439. Min Act: -0.1700

Data Index: 933976 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.7064. Min Act: -0.1700

Data Index: 143595 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.6752. Min Act: -0.1700

Data Index: 874320 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.6752. Min Act: -0.1700

Data Index: 197662 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.6752. Min Act: -0.1700

Data Index: 1107384 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.7064. Min Act: -0.1700

Data Index: 1314546 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.7064. Min Act: -0.1700

Data Index: 872923 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 5.9252. Min Range: -5.9252

Max Act: 5.6439. Min Act: -0.1700

Data Index: 458674 (C4 (Web Text))

Max Activating Token Index: 112