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

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

Neuron 1858 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.1399. Min Act: -0.1700

Data Index: 867057 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.0768. Min Act: -0.1700

Data Index: 729816 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.0610. Min Act: -0.1700

Data Index: 1231396 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.0137. Min Act: -0.1700

Data Index: 433891 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.0610. Min Act: -0.1700

Data Index: 1057193 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.0610. Min Act: -0.1700

Data Index: 448692 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.0453. Min Act: -0.1700

Data Index: 345512 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.0610. Min Act: -0.1700

Data Index: 638700 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.0295. Min Act: -0.1700

Data Index: 116068 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.0295. Min Act: -0.1700

Data Index: 1051091 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.0453. Min Act: -0.1700

Data Index: 956446 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.0295. Min Act: -0.1700

Data Index: 1316622 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.0453. Min Act: -0.1700

Data Index: 969505 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.9820. Min Act: -0.1700

Data Index: 566514 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.9979. Min Act: -0.1700

Data Index: 1027360 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.9820. Min Act: -0.1700

Data Index: 1204004 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.9979. Min Act: -0.1700

Data Index: 1345029 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 3.1399. Min Range: -3.1399

Max Act: 3.0137. Min Act: -0.1700

Data Index: 996271 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.9820. Min Act: -0.1700

Data Index: 1219128 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 3.1399. Min Range: -3.1399

Max Act: 2.9662. Min Act: -0.1700

Data Index: 1159788 (C4 (Web Text))

Max Activating Token Index: 719