Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 804 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.4117. Min Act: -0.1700

Data Index: 74351 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.2704. Min Act: -0.1699

Data Index: 891767 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.2704. Min Act: -0.1700

Data Index: 704424 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.2390. Min Act: -0.1700

Data Index: 112307 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.2233. Min Act: -0.1700

Data Index: 201486 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.2233. Min Act: -0.1700

Data Index: 985272 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.1446. Min Act: -0.1700

Data Index: 246880 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.1918. Min Act: -0.1700

Data Index: 665295 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.1761. Min Act: -0.1700

Data Index: 428287 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.1603. Min Act: -0.1700

Data Index: 407000 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.1446. Min Act: -0.1700

Data Index: 1199325 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.1603. Min Act: -0.1700

Data Index: 640490 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.1288. Min Act: -0.1700

Data Index: 850255 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.1603. Min Act: -0.1700

Data Index: 88112 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.1288. Min Act: -0.1700

Data Index: 1079194 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.1446. Min Act: -0.1700

Data Index: 1062303 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.1288. Min Act: -0.1700

Data Index: 359230 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.1603. Min Act: -0.1700

Data Index: 805643 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.0973. Min Act: -0.1700

Data Index: 892630 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 3.4117. Min Range: -3.4117

Max Act: 3.1288. Min Act: -0.1700

Data Index: 423232 (C4 (Web Text))

Max Activating Token Index: 848