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

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

Neuron 934 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: 5.5323. Min Range: -5.5323

Max Act: 5.5323. Min Act: -0.1700

Data Index: 1644157 (Python Code)

Max Activating Token Index: 541

Text #1

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.4698. Min Act: -0.1700

Data Index: 39013 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.4385. Min Act: -0.1700

Data Index: 18964 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.4073. Min Act: -0.1700

Data Index: 1634686 (Python Code)

Max Activating Token Index: 723

Text #4

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.4073. Min Act: -0.1700

Data Index: 44384 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.3135. Min Act: -0.1700

Data Index: 1498914 (Python Code)

Max Activating Token Index: 776

Text #6

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.3448. Min Act: -0.1700

Data Index: 1339940 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.3448. Min Act: -0.1700

Data Index: 319414 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.3448. Min Act: -0.1700

Data Index: 203152 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.3448. Min Act: -0.1700

Data Index: 1568175 (Python Code)

Max Activating Token Index: 852

Text #10

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.3135. Min Act: -0.1700

Data Index: 79960 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.3448. Min Act: -0.1700

Data Index: 1495998 (Python Code)

Max Activating Token Index: 870

Text #12

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.3135. Min Act: -0.1700

Data Index: 323479 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.2823. Min Act: -0.1700

Data Index: 784865 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.2510. Min Act: -0.1700

Data Index: 975989 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.2510. Min Act: -0.1700

Data Index: 806972 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.2510. Min Act: -0.1700

Data Index: 1232112 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.3135. Min Act: -0.1700

Data Index: 601059 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.2198. Min Act: -0.1700

Data Index: 110890 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 5.5323. Min Range: -5.5323

Max Act: 5.1885. Min Act: -0.1700

Data Index: 19406 (C4 (Web Text))

Max Activating Token Index: 461