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

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

Neuron 509 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: 4.8313. Min Range: -4.8313

Max Act: 4.8313. Min Act: -0.1700

Data Index: 555363 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.8000. Min Act: -0.1700

Data Index: 112934 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.7375. Min Act: -0.1700

Data Index: 1211669 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.8313. Min Act: -0.1700

Data Index: 465223 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.7375. Min Act: -0.1700

Data Index: 1020577 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.7375. Min Act: -0.1700

Data Index: 257695 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.7375. Min Act: -0.1700

Data Index: 352284 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.7375. Min Act: -0.1700

Data Index: 199742 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.6438. Min Act: -0.1700

Data Index: 222289 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.6750. Min Act: -0.1700

Data Index: 36971 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.6438. Min Act: -0.1700

Data Index: 355003 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.6125. Min Act: -0.1700

Data Index: 9552 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.6438. Min Act: -0.1700

Data Index: 1329289 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.6438. Min Act: -0.1700

Data Index: 1344132 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.6438. Min Act: -0.1700

Data Index: 96771 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.6438. Min Act: -0.1700

Data Index: 948578 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.6438. Min Act: -0.1700

Data Index: 70714 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.6125. Min Act: -0.1700

Data Index: 340689 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.6125. Min Act: -0.1700

Data Index: 330732 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 4.8313. Min Range: -4.8313

Max Act: 4.5813. Min Act: -0.1700

Data Index: 677294 (C4 (Web Text))

Max Activating Token Index: 708