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

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

Neuron 1720 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: 5.5070. Min Range: -5.5070

Max Act: 5.5070. Min Act: -0.1700

Data Index: 716702 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.3195. Min Act: -0.1700

Data Index: 1324087 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.2570. Min Act: -0.1700

Data Index: 1109726 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.2883. Min Act: -0.1700

Data Index: 957544 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.1633. Min Act: -0.1700

Data Index: 1057921 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.2258. Min Act: -0.1700

Data Index: 725761 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.1945. Min Act: -0.1700

Data Index: 1042740 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.2570. Min Act: -0.1700

Data Index: 959129 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.1008. Min Act: -0.1700

Data Index: 291456 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.1320. Min Act: -0.1700

Data Index: 997169 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.1633. Min Act: -0.1700

Data Index: 608408 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.1633. Min Act: -0.1700

Data Index: 93941 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.1320. Min Act: -0.1700

Data Index: 503136 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.0695. Min Act: -0.1700

Data Index: 374890 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.1008. Min Act: -0.1700

Data Index: 98791 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.0695. Min Act: -0.1700

Data Index: 584367 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.1008. Min Act: -0.1700

Data Index: 875683 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.1008. Min Act: -0.1700

Data Index: 1351934 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.0695. Min Act: -0.1700

Data Index: 302196 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 5.5070. Min Range: -5.5070

Max Act: 5.1008. Min Act: -0.1700

Data Index: 762606 (C4 (Web Text))

Max Activating Token Index: 179