Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1584 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.3203. Min Act: -0.1700

Data Index: 1636813 (Python Code)

Max Activating Token Index: 112

Text #1

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.2889. Min Act: -0.1700

Data Index: 1564912 (Python Code)

Max Activating Token Index: 70

Text #2

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1946. Min Act: -0.1700

Data Index: 1371986 (Python Code)

Max Activating Token Index: 997

Text #3

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0843. Min Act: -0.1700

Data Index: 913858 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0843. Min Act: -0.1700

Data Index: 684690 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0686. Min Act: -0.1700

Data Index: 1602657 (Python Code)

Max Activating Token Index: 197

Text #6

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0212. Min Act: -0.1700

Data Index: 955473 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0054. Min Act: -0.1700

Data Index: 599549 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0054. Min Act: -0.1700

Data Index: 619444 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0054. Min Act: -0.1700

Data Index: 157848 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0054. Min Act: -0.1700

Data Index: 739693 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0212. Min Act: -0.1700

Data Index: 230562 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0054. Min Act: -0.1700

Data Index: 311530 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0054. Min Act: -0.1700

Data Index: 232129 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 3.3203. Min Range: -3.3203

Max Act: 2.9579. Min Act: -0.1700

Data Index: 347159 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 3.3203. Min Range: -3.3203

Max Act: 2.9579. Min Act: -0.1700

Data Index: 1388597 (Python Code)

Max Activating Token Index: 219

Text #16

Max Range: 3.3203. Min Range: -3.3203

Max Act: 2.9738. Min Act: -0.1700

Data Index: 967412 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 3.3203. Min Range: -3.3203

Max Act: 2.9738. Min Act: -0.1700

Data Index: 445973 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 3.3203. Min Range: -3.3203

Max Act: 2.9896. Min Act: -0.1700

Data Index: 127793 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 3.3203. Min Range: -3.3203

Max Act: 2.9738. Min Act: -0.1700

Data Index: 1129822 (C4 (Web Text))

Max Activating Token Index: 493