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

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

Neuron 2031 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: 3.8109. Min Range: -3.8109

Max Act: 3.8109. Min Act: -0.1700

Data Index: 1593882 (Python Code)

Max Activating Token Index: 365

Text #1

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.7797. Min Act: -0.1700

Data Index: 1495389 (Python Code)

Max Activating Token Index: 458

Text #2

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.7484. Min Act: -0.1700

Data Index: 1505877 (Python Code)

Max Activating Token Index: 250

Text #3

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.7484. Min Act: -0.1700

Data Index: 1510668 (Python Code)

Max Activating Token Index: 343

Text #4

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.7327. Min Act: -0.1700

Data Index: 1558624 (Python Code)

Max Activating Token Index: 776

Text #5

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.7327. Min Act: -0.1700

Data Index: 1438024 (Python Code)

Max Activating Token Index: 185

Text #6

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.7014. Min Act: -0.1700

Data Index: 1464200 (Python Code)

Max Activating Token Index: 435

Text #7

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.7014. Min Act: -0.1700

Data Index: 1430275 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.7014. Min Act: -0.1700

Data Index: 1478321 (Python Code)

Max Activating Token Index: 743

Text #9

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6701. Min Act: -0.1700

Data Index: 1643369 (Python Code)

Max Activating Token Index: 840

Text #10

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6545. Min Act: -0.1700

Data Index: 1603659 (Python Code)

Max Activating Token Index: 305

Text #11

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6545. Min Act: -0.1700

Data Index: 1623532 (Python Code)

Max Activating Token Index: 659

Text #12

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6545. Min Act: -0.1700

Data Index: 1599418 (Python Code)

Max Activating Token Index: 87

Text #13

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6388. Min Act: -0.1700

Data Index: 1578975 (Python Code)

Max Activating Token Index: 359

Text #14

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6232. Min Act: -0.1700

Data Index: 1511026 (Python Code)

Max Activating Token Index: 545

Text #15

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6075. Min Act: -0.1700

Data Index: 1379164 (Python Code)

Max Activating Token Index: 507

Text #16

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6232. Min Act: -0.1700

Data Index: 1591398 (Python Code)

Max Activating Token Index: 767

Text #17

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6232. Min Act: -0.1700

Data Index: 1504561 (Python Code)

Max Activating Token Index: 389

Text #18

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6232. Min Act: -0.1700

Data Index: 1396308 (Python Code)

Max Activating Token Index: 671

Text #19

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6075. Min Act: -0.1700

Data Index: 1587572 (Python Code)

Max Activating Token Index: 741