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

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

Neuron 980 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: 5.7379. Min Range: -5.7379

Max Act: 5.7379. Min Act: -0.1700

Data Index: 1090312 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.7067. Min Act: -0.1700

Data Index: 1157944 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.7067. Min Act: -0.1700

Data Index: 369280 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.6442. Min Act: -0.1700

Data Index: 842520 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.6442. Min Act: -0.1700

Data Index: 126875 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.6129. Min Act: -0.1700

Data Index: 844081 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.6129. Min Act: -0.1700

Data Index: 1290780 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.6129. Min Act: -0.1700

Data Index: 1307085 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.6442. Min Act: -0.1700

Data Index: 51629 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.6129. Min Act: -0.1700

Data Index: 638411 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.5192. Min Act: -0.1700

Data Index: 891076 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.5504. Min Act: -0.1700

Data Index: 801197 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.5817. Min Act: -0.1700

Data Index: 835534 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.5817. Min Act: -0.1700

Data Index: 480051 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.5817. Min Act: -0.1700

Data Index: 552116 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.5504. Min Act: -0.1700

Data Index: 1046752 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.5817. Min Act: -0.1700

Data Index: 966939 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.5192. Min Act: -0.1700

Data Index: 664098 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.5192. Min Act: -0.1700

Data Index: 584800 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 5.7379. Min Range: -5.7379

Max Act: 5.5192. Min Act: -0.1700

Data Index: 1250297 (C4 (Web Text))

Max Activating Token Index: 389