Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 667 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 8.4573. Min Range: -8.4573

Max Act: 8.4261. Min Act: -0.1700

Data Index: 1135034 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 8.4573. Min Range: -8.4573

Max Act: 8.0511. Min Act: -0.1700

Data Index: 431578 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 8.4573. Min Range: -8.4573

Max Act: 8.4573. Min Act: -0.1700

Data Index: 863661 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 8.4573. Min Range: -8.4573

Max Act: 8.1136. Min Act: -0.1700

Data Index: 304522 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 8.4573. Min Range: -8.4573

Max Act: 8.3323. Min Act: -0.1700

Data Index: 274675 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 8.4573. Min Range: -8.4573

Max Act: 8.2386. Min Act: -0.1700

Data Index: 405020 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 8.4573. Min Range: -8.4573

Max Act: 8.1448. Min Act: -0.1700

Data Index: 243638 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 8.4573. Min Range: -8.4573

Max Act: 7.8948. Min Act: -0.1700

Data Index: 955701 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 8.4573. Min Range: -8.4573

Max Act: 7.9573. Min Act: -0.1700

Data Index: 400809 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 8.4573. Min Range: -8.4573

Max Act: 7.8636. Min Act: -0.1700

Data Index: 425828 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 8.4573. Min Range: -8.4573

Max Act: 8.0511. Min Act: -0.1700

Data Index: 97377 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 8.4573. Min Range: -8.4573

Max Act: 7.8011. Min Act: -0.1700

Data Index: 895789 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 8.4573. Min Range: -8.4573

Max Act: 8.0511. Min Act: -0.1700

Data Index: 1535017 (Python Code)

Max Activating Token Index: 56

Text #13

Max Range: 8.4573. Min Range: -8.4573

Max Act: 8.0511. Min Act: -0.1700

Data Index: 1219453 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 8.4573. Min Range: -8.4573

Max Act: 8.0823. Min Act: -0.1700

Data Index: 130465 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 8.4573. Min Range: -8.4573

Max Act: 7.9886. Min Act: -0.1700

Data Index: 457063 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 8.4573. Min Range: -8.4573

Max Act: 8.2073. Min Act: -0.1700

Data Index: 683340 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 8.4573. Min Range: -8.4573

Max Act: 7.9573. Min Act: -0.1700

Data Index: 135727 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 8.4573. Min Range: -8.4573

Max Act: 7.9261. Min Act: -0.1700

Data Index: 170442 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 8.4573. Min Range: -8.4573

Max Act: 7.9886. Min Act: -0.1700

Data Index: 766885 (C4 (Web Text))

Max Activating Token Index: 177