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

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

Neuron 837 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.3220. Min Act: -0.1700

Data Index: 1182067 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.2908. Min Act: -0.1700

Data Index: 334329 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1970. Min Act: -0.1700

Data Index: 1484373 (Python Code)

Max Activating Token Index: 728

Text #3

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.2283. Min Act: -0.1700

Data Index: 1482699 (Python Code)

Max Activating Token Index: 713

Text #4

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1970. Min Act: -0.1700

Data Index: 1639479 (Python Code)

Max Activating Token Index: 693

Text #5

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1658. Min Act: -0.1700

Data Index: 1423897 (Python Code)

Max Activating Token Index: 637

Text #6

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1658. Min Act: -0.1700

Data Index: 1590133 (Python Code)

Max Activating Token Index: 328

Text #7

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1658. Min Act: -0.1700

Data Index: 1552080 (Python Code)

Max Activating Token Index: 565

Text #8

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1658. Min Act: -0.1700

Data Index: 351367 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1345. Min Act: -0.1700

Data Index: 587565 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1658. Min Act: -0.1700

Data Index: 1407920 (Python Code)

Max Activating Token Index: 265

Text #11

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1658. Min Act: -0.1700

Data Index: 1407712 (Python Code)

Max Activating Token Index: 614

Text #12

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1345. Min Act: -0.1700

Data Index: 1436798 (Python Code)

Max Activating Token Index: 430

Text #13

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1345. Min Act: -0.1700

Data Index: 329366 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1345. Min Act: -0.1700

Data Index: 1546077 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1658. Min Act: -0.1700

Data Index: 1548169 (Python Code)

Max Activating Token Index: 579

Text #16

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1658. Min Act: -0.1700

Data Index: 1459413 (Python Code)

Max Activating Token Index: 584

Text #17

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1345. Min Act: -0.1700

Data Index: 1390521 (Python Code)

Max Activating Token Index: 453

Text #18

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1658. Min Act: -0.1700

Data Index: 1573953 (Python Code)

Max Activating Token Index: 627

Text #19

Max Range: 5.3220. Min Range: -5.3220

Max Act: 5.1658. Min Act: -0.1700

Data Index: 1458217 (Python Code)

Max Activating Token Index: 195