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

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

Neuron 1293 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: 3.1941. Min Range: -3.1941

Max Act: 3.1941. Min Act: -0.1700

Data Index: 1472160 (Python Code)

Max Activating Token Index: 461

Text #1

Max Range: 3.1941. Min Range: -3.1941

Max Act: 3.0750. Min Act: -0.1700

Data Index: 1497381 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 3.1941. Min Range: -3.1941

Max Act: 3.0512. Min Act: -0.1700

Data Index: 1081366 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 3.1941. Min Range: -3.1941

Max Act: 3.0324. Min Act: -0.1700

Data Index: 1573721 (Python Code)

Max Activating Token Index: 179

Text #4

Max Range: 3.1941. Min Range: -3.1941

Max Act: 3.0119. Min Act: -0.1700

Data Index: 1582079 (Python Code)

Max Activating Token Index: 719

Text #5

Max Range: 3.1941. Min Range: -3.1941

Max Act: 3.0020. Min Act: -0.1700

Data Index: 58282 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9992. Min Act: -0.1700

Data Index: 1643827 (Python Code)

Max Activating Token Index: 922

Text #7

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9991. Min Act: -0.1700

Data Index: 1452913 (Python Code)

Max Activating Token Index: 568

Text #8

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9848. Min Act: -0.1700

Data Index: 1231214 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9755. Min Act: -0.1700

Data Index: 1482475 (Python Code)

Max Activating Token Index: 527

Text #10

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9728. Min Act: -0.1700

Data Index: 1380784 (Python Code)

Max Activating Token Index: 570

Text #11

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9658. Min Act: -0.1700

Data Index: 1411377 (Python Code)

Max Activating Token Index: 667

Text #12

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9842. Min Act: -0.1700

Data Index: 1390775 (Python Code)

Max Activating Token Index: 491

Text #13

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9662. Min Act: -0.1700

Data Index: 948314 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9685. Min Act: -0.1700

Data Index: 1455211 (Python Code)

Max Activating Token Index: 211

Text #15

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9565. Min Act: -0.1700

Data Index: 1438696 (Python Code)

Max Activating Token Index: 240

Text #16

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9406. Min Act: -0.1700

Data Index: 869049 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9606. Min Act: -0.1700

Data Index: 855859 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9420. Min Act: -0.1700

Data Index: 1588987 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 3.1941. Min Range: -3.1941

Max Act: 2.9324. Min Act: -0.1700

Data Index: 166427 (C4 (Web Text))

Max Activating Token Index: 905