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

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

Neuron 1544 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: 3.7116. Min Range: -3.7116

Max Act: 3.7116. Min Act: -0.1700

Data Index: 923533 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.7116. Min Act: -0.1700

Data Index: 1347464 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.7116. Min Act: -0.1700

Data Index: 688875 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.5237. Min Act: -0.1700

Data Index: 533924 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.4924. Min Act: -0.1700

Data Index: 678330 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.4924. Min Act: -0.1700

Data Index: 597354 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.4610. Min Act: -0.1700

Data Index: 289891 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.4610. Min Act: -0.1700

Data Index: 770519 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.4610. Min Act: -0.1700

Data Index: 1040958 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.4610. Min Act: -0.1700

Data Index: 1033265 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.4297. Min Act: -0.1700

Data Index: 715165 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.4610. Min Act: -0.1700

Data Index: 548639 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.4610. Min Act: -0.1700

Data Index: 977242 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.4297. Min Act: -0.1700

Data Index: 963674 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.4297. Min Act: -0.1700

Data Index: 70237 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.4297. Min Act: -0.1700

Data Index: 1346658 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.3983. Min Act: -0.1700

Data Index: 988037 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.3983. Min Act: -0.1700

Data Index: 1253959 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.3983. Min Act: -0.1700

Data Index: 915648 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.3670. Min Act: -0.1700

Data Index: 1642849 (Python Code)

Max Activating Token Index: 5