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

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

Neuron 653 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: 3.4454. Min Range: -3.4454

Max Act: 3.4454. Min Act: -0.1700

Data Index: 1530166 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.3764. Min Act: -0.1700

Data Index: 1562883 (Python Code)

Max Activating Token Index: 767

Text #2

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.1717. Min Act: -0.1700

Data Index: 1410734 (Python Code)

Max Activating Token Index: 977

Text #3

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.0975. Min Act: -0.1700

Data Index: 1447527 (Python Code)

Max Activating Token Index: 863

Text #4

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.0774. Min Act: -0.1700

Data Index: 1496245 (Python Code)

Max Activating Token Index: 146

Text #5

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.0882. Min Act: -0.1700

Data Index: 1619629 (Python Code)

Max Activating Token Index: 209

Text #6

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.0688. Min Act: -0.1700

Data Index: 1499032 (Python Code)

Max Activating Token Index: 765

Text #7

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.0631. Min Act: -0.1700

Data Index: 1509649 (Python Code)

Max Activating Token Index: 162

Text #8

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.0507. Min Act: -0.1700

Data Index: 73594 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1636626 (Python Code)

Max Activating Token Index: 353

Text #10

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.0298. Min Act: -0.1700

Data Index: 1555165 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.0201. Min Act: -0.1700

Data Index: 1595534 (Python Code)

Max Activating Token Index: 555

Text #12

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.0304. Min Act: -0.1700

Data Index: 437253 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.0118. Min Act: -0.1700

Data Index: 1652420 (Python Code)

Max Activating Token Index: 137

Text #14

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.0175. Min Act: -0.1700

Data Index: 1588699 (Python Code)

Max Activating Token Index: 130

Text #15

Max Range: 3.4454. Min Range: -3.4454

Max Act: 2.9983. Min Act: -0.1700

Data Index: 1510243 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 3.4454. Min Range: -3.4454

Max Act: 3.0047. Min Act: -0.1700

Data Index: 1377210 (Python Code)

Max Activating Token Index: 897

Text #17

Max Range: 3.4454. Min Range: -3.4454

Max Act: 2.9750. Min Act: -0.1700

Data Index: 1372697 (Python Code)

Max Activating Token Index: 302

Text #18

Max Range: 3.4454. Min Range: -3.4454

Max Act: 2.9814. Min Act: -0.1700

Data Index: 1397454 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 3.4454. Min Range: -3.4454

Max Act: 2.9621. Min Act: -0.1700

Data Index: 1455209 (Python Code)

Max Activating Token Index: 741