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

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

Neuron 1398 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1542. Min Range: -3.1542

Max Act: 3.1542. Min Act: -0.1700

Data Index: 667405 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 3.1542. Min Range: -3.1542

Max Act: 3.1069. Min Act: -0.1700

Data Index: 516851 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 3.1542. Min Range: -3.1542

Max Act: 3.0912. Min Act: -0.1700

Data Index: 615247 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 3.1542. Min Range: -3.1542

Max Act: 3.0280. Min Act: -0.1700

Data Index: 857233 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9964. Min Act: -0.1700

Data Index: 165395 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9806. Min Act: -0.1700

Data Index: 141453 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9490. Min Act: -0.1700

Data Index: 4537 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9806. Min Act: -0.1700

Data Index: 175330 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9648. Min Act: -0.1700

Data Index: 343588 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9490. Min Act: -0.1700

Data Index: 699596 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9648. Min Act: -0.1700

Data Index: 1233088 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9648. Min Act: -0.1700

Data Index: 340112 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9490. Min Act: -0.1700

Data Index: 1254377 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9490. Min Act: -0.1700

Data Index: 778190 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9648. Min Act: -0.1700

Data Index: 608744 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9331. Min Act: -0.1700

Data Index: 61025 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9490. Min Act: -0.1700

Data Index: 1029189 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9331. Min Act: -0.1700

Data Index: 105808 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9173. Min Act: -0.1700

Data Index: 289165 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9014. Min Act: -0.1700

Data Index: 1040830 (C4 (Web Text))

Max Activating Token Index: 456