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

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

Neuron 1620 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: 3.0855. Min Range: -3.0855

Max Act: 3.0855. Min Act: -0.1700

Data Index: 1203742 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 3.0855. Min Range: -3.0855

Max Act: 3.0539. Min Act: -0.1700

Data Index: 1143582 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 3.0855. Min Range: -3.0855

Max Act: 3.0539. Min Act: -0.1700

Data Index: 472767 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 3.0855. Min Range: -3.0855

Max Act: 3.0382. Min Act: -0.1700

Data Index: 451845 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 3.0855. Min Range: -3.0855

Max Act: 3.0382. Min Act: -0.1700

Data Index: 1022453 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 3.0855. Min Range: -3.0855

Max Act: 3.0224. Min Act: -0.1700

Data Index: 1037164 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 3.0855. Min Range: -3.0855

Max Act: 3.0066. Min Act: -0.1700

Data Index: 1214182 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 3.0855. Min Range: -3.0855

Max Act: 3.0066. Min Act: -0.1700

Data Index: 382009 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 3.0855. Min Range: -3.0855

Max Act: 3.0224. Min Act: -0.1700

Data Index: 932563 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 3.0855. Min Range: -3.0855

Max Act: 3.0066. Min Act: -0.1700

Data Index: 928775 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 3.0855. Min Range: -3.0855

Max Act: 2.9907. Min Act: -0.1700

Data Index: 534692 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 3.0855. Min Range: -3.0855

Max Act: 2.9749. Min Act: -0.1700

Data Index: 61277 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 3.0855. Min Range: -3.0855

Max Act: 2.9749. Min Act: -0.1700

Data Index: 967609 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 3.0855. Min Range: -3.0855

Max Act: 2.9749. Min Act: -0.1700

Data Index: 516445 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 3.0855. Min Range: -3.0855

Max Act: 2.9749. Min Act: -0.1700

Data Index: 513112 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 3.0855. Min Range: -3.0855

Max Act: 2.9591. Min Act: -0.1700

Data Index: 219627 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 3.0855. Min Range: -3.0855

Max Act: 2.9907. Min Act: -0.1700

Data Index: 284441 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 3.0855. Min Range: -3.0855

Max Act: 2.9749. Min Act: -0.1700

Data Index: 600741 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 3.0855. Min Range: -3.0855

Max Act: 2.9907. Min Act: -0.1700

Data Index: 606479 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 3.0855. Min Range: -3.0855

Max Act: 2.9749. Min Act: -0.1700

Data Index: 153043 (C4 (Web Text))

Max Activating Token Index: 654