Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 18 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.5536. Min Act: -0.1700

Data Index: 517484 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.4440. Min Act: -0.1700

Data Index: 614412 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3969. Min Act: -0.1700

Data Index: 594481 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.4126. Min Act: -0.1700

Data Index: 894644 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3498. Min Act: -0.1700

Data Index: 998202 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3655. Min Act: -0.1700

Data Index: 1132526 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3498. Min Act: -0.1700

Data Index: 575198 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3498. Min Act: -0.1700

Data Index: 640987 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3655. Min Act: -0.1700

Data Index: 301094 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3498. Min Act: -0.1700

Data Index: 501962 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3498. Min Act: -0.1700

Data Index: 259672 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3498. Min Act: -0.1700

Data Index: 421494 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3498. Min Act: -0.1700

Data Index: 253514 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3341. Min Act: -0.1700

Data Index: 550560 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3184. Min Act: -0.1700

Data Index: 619863 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3341. Min Act: -0.1700

Data Index: 1101621 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3184. Min Act: -0.1700

Data Index: 836372 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3184. Min Act: -0.1700

Data Index: 471009 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3184. Min Act: -0.1700

Data Index: 909119 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 3.5536. Min Range: -3.5536

Max Act: 3.3027. Min Act: -0.1700

Data Index: 883692 (C4 (Web Text))

Max Activating Token Index: 31