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

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

Neuron 1910 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: 7.5543. Min Range: -7.5543

Max Act: 7.5543. Min Act: -0.1700

Data Index: 1547921 (Python Code)

Max Activating Token Index: 677

Text #1

Max Range: 7.5543. Min Range: -7.5543

Max Act: 7.4721. Min Act: -0.1700

Data Index: 1389945 (Python Code)

Max Activating Token Index: 320

Text #2

Max Range: 7.5543. Min Range: -7.5543

Max Act: 7.4004. Min Act: -0.1700

Data Index: 1413265 (Python Code)

Max Activating Token Index: 35

Text #3

Max Range: 7.5543. Min Range: -7.5543

Max Act: 7.2101. Min Act: -0.1700

Data Index: 1498600 (Python Code)

Max Activating Token Index: 246

Text #4

Max Range: 7.5543. Min Range: -7.5543

Max Act: 7.1358. Min Act: -0.1700

Data Index: 1467276 (Python Code)

Max Activating Token Index: 437

Text #5

Max Range: 7.5543. Min Range: -7.5543

Max Act: 7.0846. Min Act: -0.1700

Data Index: 1443158 (Python Code)

Max Activating Token Index: 306

Text #6

Max Range: 7.5543. Min Range: -7.5543

Max Act: 7.1079. Min Act: -0.1700

Data Index: 1623504 (Python Code)

Max Activating Token Index: 48

Text #7

Max Range: 7.5543. Min Range: -7.5543

Max Act: 7.0689. Min Act: -0.1700

Data Index: 1645764 (Python Code)

Max Activating Token Index: 251

Text #8

Max Range: 7.5543. Min Range: -7.5543

Max Act: 7.0109. Min Act: -0.1700

Data Index: 1381517 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 7.5543. Min Range: -7.5543

Max Act: 7.0133. Min Act: -0.1700

Data Index: 1581200 (Python Code)

Max Activating Token Index: 742

Text #10

Max Range: 7.5543. Min Range: -7.5543

Max Act: 7.0070. Min Act: -0.1700

Data Index: 1509026 (Python Code)

Max Activating Token Index: 853

Text #11

Max Range: 7.5543. Min Range: -7.5543

Max Act: 6.9412. Min Act: -0.1700

Data Index: 1532124 (Python Code)

Max Activating Token Index: 981

Text #12

Max Range: 7.5543. Min Range: -7.5543

Max Act: 6.9320. Min Act: -0.1700

Data Index: 1370155 (Python Code)

Max Activating Token Index: 724

Text #13

Max Range: 7.5543. Min Range: -7.5543

Max Act: 6.9340. Min Act: -0.1700

Data Index: 1431954 (Python Code)

Max Activating Token Index: 894

Text #14

Max Range: 7.5543. Min Range: -7.5543

Max Act: 6.9847. Min Act: -0.1700

Data Index: 1569132 (Python Code)

Max Activating Token Index: 429

Text #15

Max Range: 7.5543. Min Range: -7.5543

Max Act: 6.9919. Min Act: -0.1700

Data Index: 1485822 (Python Code)

Max Activating Token Index: 742

Text #16

Max Range: 7.5543. Min Range: -7.5543

Max Act: 6.9703. Min Act: -0.1699

Data Index: 1614931 (Python Code)

Max Activating Token Index: 1003

Text #17

Max Range: 7.5543. Min Range: -7.5543

Max Act: 6.9495. Min Act: -0.1700

Data Index: 1389433 (Python Code)

Max Activating Token Index: 987

Text #18

Max Range: 7.5543. Min Range: -7.5543

Max Act: 6.9696. Min Act: -0.1700

Data Index: 1592043 (Python Code)

Max Activating Token Index: 27

Text #19

Max Range: 7.5543. Min Range: -7.5543

Max Act: 7.0287. Min Act: -0.1700

Data Index: 1616372 (Python Code)

Max Activating Token Index: 933