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

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

Neuron 1361 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: 3.8983. Min Range: -3.8983

Max Act: 3.8983. Min Act: -0.1700

Data Index: 977186 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.8513. Min Act: -0.1700

Data Index: 889694 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.8826. Min Act: -0.1700

Data Index: 1026334 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.8670. Min Act: -0.1700

Data Index: 1264333 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.8044. Min Act: -0.1700

Data Index: 651546 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.7731. Min Act: -0.1700

Data Index: 639287 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.7575. Min Act: -0.1700

Data Index: 804666 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.7731. Min Act: -0.1700

Data Index: 1210864 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.7419. Min Act: -0.1700

Data Index: 596855 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.7419. Min Act: -0.1700

Data Index: 1090451 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.6949. Min Act: -0.1700

Data Index: 750510 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.6949. Min Act: -0.1700

Data Index: 70659 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.6793. Min Act: -0.1700

Data Index: 489835 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.7262. Min Act: -0.1700

Data Index: 559290 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.6793. Min Act: -0.1700

Data Index: 237771 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.6949. Min Act: -0.1700

Data Index: 364079 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.6480. Min Act: -0.1700

Data Index: 1037781 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.6636. Min Act: -0.1700

Data Index: 674447 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.6636. Min Act: -0.1700

Data Index: 425322 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 3.8983. Min Range: -3.8983

Max Act: 3.6480. Min Act: -0.1700

Data Index: 397268 (C4 (Web Text))

Max Activating Token Index: 763