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

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

Neuron 722 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: 2.8938. Min Range: -2.8938

Max Act: 2.8938. Min Act: -0.1700

Data Index: 1397858 (Python Code)

Max Activating Token Index: 257

Text #1

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.8772. Min Act: -0.1700

Data Index: 1389866 (Python Code)

Max Activating Token Index: 705

Text #2

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.8525. Min Act: -0.1700

Data Index: 1374704 (Python Code)

Max Activating Token Index: 154

Text #3

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.8379. Min Act: -0.1700

Data Index: 519281 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.8049. Min Act: -0.1700

Data Index: 1551337 (Python Code)

Max Activating Token Index: 231

Text #5

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.7804. Min Act: -0.1696

Data Index: 1575661 (Python Code)

Max Activating Token Index: 299

Text #6

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.7753. Min Act: -0.1700

Data Index: 549240 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.7570. Min Act: -0.1700

Data Index: 339244 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.7521. Min Act: -0.1700

Data Index: 835714 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.7513. Min Act: -0.1700

Data Index: 1262534 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.7512. Min Act: -0.1700

Data Index: 1395902 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.7473. Min Act: -0.1699

Data Index: 1370272 (Python Code)

Max Activating Token Index: 46

Text #12

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.7235. Min Act: -0.1699

Data Index: 1654215 (Python Code)

Max Activating Token Index: 356

Text #13

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.7348. Min Act: -0.1700

Data Index: 152772 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.6997. Min Act: -0.1700

Data Index: 1615582 (Python Code)

Max Activating Token Index: 90

Text #15

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.7006. Min Act: -0.1700

Data Index: 421736 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.6920. Min Act: -0.1700

Data Index: 1357785 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.7007. Min Act: -0.1700

Data Index: 1651849 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.6911. Min Act: -0.1699

Data Index: 1477062 (Python Code)

Max Activating Token Index: 580

Text #19

Max Range: 2.8938. Min Range: -2.8938

Max Act: 2.6706. Min Act: -0.1700

Data Index: 1476612 (Python Code)

Max Activating Token Index: 1019