Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 659 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.1057. Min Act: -0.1700

Data Index: 223131 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.1215. Min Act: -0.1700

Data Index: 533135 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0899. Min Act: -0.1700

Data Index: 601594 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0742. Min Act: -0.1700

Data Index: 1022361 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0426. Min Act: -0.1700

Data Index: 437047 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0426. Min Act: -0.1700

Data Index: 731062 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0426. Min Act: -0.1700

Data Index: 281617 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0426. Min Act: -0.1700

Data Index: 1139735 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0426. Min Act: -0.1700

Data Index: 746633 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0110. Min Act: -0.1700

Data Index: 779202 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0268. Min Act: -0.1700

Data Index: 318302 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9952. Min Act: -0.1700

Data Index: 817976 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0110. Min Act: -0.1700

Data Index: 226997 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0110. Min Act: -0.1700

Data Index: 169554 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9794. Min Act: -0.1700

Data Index: 11630 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.0110. Min Act: -0.1700

Data Index: 1137544 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9794. Min Act: -0.1700

Data Index: 1155133 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9952. Min Act: -0.1700

Data Index: 843511 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9636. Min Act: -0.1700

Data Index: 790279 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9952. Min Act: -0.1700

Data Index: 326177 (C4 (Web Text))

Max Activating Token Index: 784