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

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

Neuron 1090 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: 3.8582. Min Range: -3.8582

Max Act: 3.8582. Min Act: -0.1700

Data Index: 766085 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.8313. Min Act: -0.1700

Data Index: 500029 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.7313. Min Act: -0.1700

Data Index: 926722 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.7551. Min Act: -0.1700

Data Index: 204890 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.6858. Min Act: -0.1700

Data Index: 1468787 (Python Code)

Max Activating Token Index: 73

Text #5

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.6679. Min Act: -0.1700

Data Index: 1363488 (Python Code)

Max Activating Token Index: 351

Text #6

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.6611. Min Act: -0.1700

Data Index: 663335 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.6932. Min Act: -0.1700

Data Index: 967157 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.6711. Min Act: -0.1700

Data Index: 100190 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.5906. Min Act: -0.1700

Data Index: 366197 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.5959. Min Act: -0.1700

Data Index: 1373188 (Python Code)

Max Activating Token Index: 203

Text #11

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.6468. Min Act: -0.1700

Data Index: 1366596 (Python Code)

Max Activating Token Index: 655

Text #12

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.6225. Min Act: -0.1699

Data Index: 1373406 (Python Code)

Max Activating Token Index: 728

Text #13

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.6306. Min Act: -0.1700

Data Index: 1420730 (Python Code)

Max Activating Token Index: 504

Text #14

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.6273. Min Act: -0.1700

Data Index: 1095707 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.5886. Min Act: -0.1700

Data Index: 1083843 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.5949. Min Act: -0.1700

Data Index: 647625 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.6363. Min Act: -0.1700

Data Index: 957968 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.5704. Min Act: -0.1700

Data Index: 1085025 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 3.8582. Min Range: -3.8582

Max Act: 3.5339. Min Act: -0.1699

Data Index: 1631866 (Python Code)

Max Activating Token Index: 307