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

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

Neuron 1383 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: 7.4441. Min Range: -7.4441

Max Act: 7.2879. Min Act: -0.1700

Data Index: 93801 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 7.4441. Min Range: -7.4441

Max Act: 7.4441. Min Act: -0.1700

Data Index: 929156 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 7.4441. Min Range: -7.4441

Max Act: 7.2566. Min Act: -0.1700

Data Index: 1117460 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 7.4441. Min Range: -7.4441

Max Act: 7.1941. Min Act: -0.1699

Data Index: 1323966 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.9441. Min Act: -0.1700

Data Index: 948402 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 7.4441. Min Range: -7.4441

Max Act: 7.0066. Min Act: -0.1700

Data Index: 527855 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.9129. Min Act: -0.1700

Data Index: 685702 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.8504. Min Act: -0.1700

Data Index: 1354274 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.9441. Min Act: -0.1700

Data Index: 554954 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.9754. Min Act: -0.1700

Data Index: 14922 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.9129. Min Act: -0.1700

Data Index: 680781 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.8816. Min Act: -0.1700

Data Index: 321241 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.8816. Min Act: -0.1700

Data Index: 795203 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.7566. Min Act: -0.1700

Data Index: 266860 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.7566. Min Act: -0.1699

Data Index: 1145985 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.7566. Min Act: -0.1700

Data Index: 894763 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.8191. Min Act: -0.1700

Data Index: 1287434 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.7879. Min Act: -0.1700

Data Index: 1178133 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.7879. Min Act: -0.1700

Data Index: 595621 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 7.4441. Min Range: -7.4441

Max Act: 6.7879. Min Act: -0.1700

Data Index: 862934 (C4 (Web Text))

Max Activating Token Index: 244