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

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

Neuron 920 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.6636. Min Act: -0.1700

Data Index: 1040780 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.5386. Min Act: -0.1700

Data Index: 1043035 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.5698. Min Act: -0.1700

Data Index: 932622 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.5698. Min Act: -0.1700

Data Index: 864373 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.5698. Min Act: -0.1700

Data Index: 156775 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.5386. Min Act: -0.1700

Data Index: 147668 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.5698. Min Act: -0.1700

Data Index: 886606 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.5698. Min Act: -0.1700

Data Index: 182529 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.5073. Min Act: -0.1700

Data Index: 268629 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.5386. Min Act: -0.1700

Data Index: 700112 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.4761. Min Act: -0.1700

Data Index: 106125 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.5386. Min Act: -0.1700

Data Index: 159968 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.4448. Min Act: -0.1700

Data Index: 989574 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.4761. Min Act: -0.1700

Data Index: 154268 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.4761. Min Act: -0.1700

Data Index: 1230157 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.4761. Min Act: -0.1700

Data Index: 1215265 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.4448. Min Act: -0.1700

Data Index: 533706 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.3823. Min Act: -0.1700

Data Index: 1192659 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.4761. Min Act: -0.1699

Data Index: 508142 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 5.6636. Min Range: -5.6636

Max Act: 5.3823. Min Act: -0.1700

Data Index: 516023 (C4 (Web Text))

Max Activating Token Index: 98