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

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

Neuron 568 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: 5.8047. Min Range: -5.8047

Max Act: 5.8047. Min Act: -0.1700

Data Index: 328409 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.8047. Min Act: -0.1700

Data Index: 371155 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.6172. Min Act: -0.1700

Data Index: 1278007 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.6172. Min Act: -0.1700

Data Index: 1298556 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.6484. Min Act: -0.1700

Data Index: 495932 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.5547. Min Act: -0.1700

Data Index: 142657 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4609. Min Act: -0.1700

Data Index: 238362 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4297. Min Act: -0.1700

Data Index: 414503 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4297. Min Act: -0.1700

Data Index: 903228 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4297. Min Act: -0.1700

Data Index: 342605 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4609. Min Act: -0.1700

Data Index: 616010 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4297. Min Act: -0.1700

Data Index: 867280 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4297. Min Act: -0.1700

Data Index: 713024 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4609. Min Act: -0.1700

Data Index: 611221 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.3672. Min Act: -0.1700

Data Index: 588858 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.3984. Min Act: -0.1700

Data Index: 312237 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4297. Min Act: -0.1700

Data Index: 526753 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.3984. Min Act: -0.1700

Data Index: 967308 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.3672. Min Act: -0.1700

Data Index: 1297735 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.3359. Min Act: -0.1700

Data Index: 780330 (C4 (Web Text))

Max Activating Token Index: 691