Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 871 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.2845. Min Act: -0.1700

Data Index: 137467 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.1114. Min Act: -0.1700

Data Index: 318771 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.1114. Min Act: -0.1700

Data Index: 1349277 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.0957. Min Act: -0.1700

Data Index: 681499 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.0799. Min Act: -0.1700

Data Index: 133010 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.0325. Min Act: -0.1700

Data Index: 1118884 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.0325. Min Act: -0.1700

Data Index: 432282 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.0641. Min Act: -0.1700

Data Index: 867582 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.0483. Min Act: -0.1700

Data Index: 1356139 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.0325. Min Act: -0.1700

Data Index: 123747 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.0167. Min Act: -0.1700

Data Index: 587323 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.0641. Min Act: -0.1700

Data Index: 469906 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 3.2845. Min Range: -3.2845

Max Act: 2.9851. Min Act: -0.1700

Data Index: 376549 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.0167. Min Act: -0.1700

Data Index: 129958 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 3.2845. Min Range: -3.2845

Max Act: 3.0167. Min Act: -0.1700

Data Index: 1214731 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 3.2845. Min Range: -3.2845

Max Act: 2.9851. Min Act: -0.1700

Data Index: 1161255 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 3.2845. Min Range: -3.2845

Max Act: 2.9693. Min Act: -0.1700

Data Index: 271687 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 3.2845. Min Range: -3.2845

Max Act: 2.9851. Min Act: -0.1700

Data Index: 122684 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 3.2845. Min Range: -3.2845

Max Act: 2.9693. Min Act: -0.1700

Data Index: 298588 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 3.2845. Min Range: -3.2845

Max Act: 2.9693. Min Act: -0.1700

Data Index: 939109 (C4 (Web Text))

Max Activating Token Index: 13