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

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

Neuron 169 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: 4.1939. Min Range: -4.1939

Max Act: 4.1939. Min Act: -0.1700

Data Index: 136099 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0845. Min Act: -0.1700

Data Index: 107494 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0689. Min Act: -0.1688

Data Index: 189852 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 4.1939. Min Range: -4.1939

Max Act: 4.0063. Min Act: -0.1700

Data Index: 1077729 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.9907. Min Act: -0.1698

Data Index: 902174 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.9282. Min Act: -0.1700

Data Index: 513364 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.9282. Min Act: -0.1700

Data Index: 1309105 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.9282. Min Act: -0.1700

Data Index: 177589 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.9125. Min Act: -0.1700

Data Index: 1162219 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.9282. Min Act: -0.1700

Data Index: 1166965 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.8969. Min Act: -0.1700

Data Index: 1212710 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.8969. Min Act: -0.1700

Data Index: 897205 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.8969. Min Act: -0.1700

Data Index: 930645 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.8656. Min Act: -0.1700

Data Index: 1090370 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.8813. Min Act: -0.1700

Data Index: 1263658 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.8656. Min Act: -0.1694

Data Index: 1141831 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.8422. Min Act: -0.1700

Data Index: 186255 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.8656. Min Act: -0.1700

Data Index: 780416 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.8500. Min Act: -0.1700

Data Index: 1333238 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 4.1939. Min Range: -4.1939

Max Act: 3.8500. Min Act: -0.1700

Data Index: 451984 (C4 (Web Text))

Max Activating Token Index: 206