Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 518 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.3109. Min Act: -0.1700

Data Index: 1295521 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.2950. Min Act: -0.1700

Data Index: 1010280 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.2328. Min Act: -0.1700

Data Index: 206669 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.2136. Min Act: -0.1697

Data Index: 1408309 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.2157. Min Act: -0.1700

Data Index: 635407 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1962. Min Act: -0.1700

Data Index: 733763 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1957. Min Act: -0.1700

Data Index: 604680 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1684. Min Act: -0.1699

Data Index: 1416710 (Python Code)

Max Activating Token Index: 791

Text #8

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1551. Min Act: -0.1700

Data Index: 948582 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1718. Min Act: -0.1700

Data Index: 314742 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1496. Min Act: -0.1700

Data Index: 1263797 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1525. Min Act: -0.1590

Data Index: 101558 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1472. Min Act: -0.1700

Data Index: 1009454 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1228. Min Act: -0.1691

Data Index: 166239 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1318. Min Act: -0.1700

Data Index: 806453 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1393. Min Act: -0.1700

Data Index: 298616 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1362162 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1079. Min Act: -0.1700

Data Index: 96439 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1092. Min Act: -0.1700

Data Index: 74258 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 3.3109. Min Range: -3.3109

Max Act: 3.1238. Min Act: -0.1687

Data Index: 183199 (C4 (Web Text))

Max Activating Token Index: 213