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

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

Neuron 486 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.1363. Min Act: -0.1700

Data Index: 544870 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0890. Min Act: -0.1700

Data Index: 957171 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0575. Min Act: -0.1700

Data Index: 1089246 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0575. Min Act: -0.1700

Data Index: 471197 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0575. Min Act: -0.1700

Data Index: 458663 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0417. Min Act: -0.1700

Data Index: 913314 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0259. Min Act: -0.1700

Data Index: 137050 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 3.1363. Min Range: -3.1363

Max Act: 3.0101. Min Act: -0.1700

Data Index: 233603 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9943. Min Act: -0.1700

Data Index: 963388 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9785. Min Act: -0.1700

Data Index: 986694 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9626. Min Act: -0.1700

Data Index: 509900 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9310. Min Act: -0.1700

Data Index: 979056 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9310. Min Act: -0.1700

Data Index: 371742 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9151. Min Act: -0.1700

Data Index: 933113 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9151. Min Act: -0.1700

Data Index: 729162 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9151. Min Act: -0.1700

Data Index: 1260093 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9151. Min Act: -0.1700

Data Index: 1079665 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.8993. Min Act: -0.1700

Data Index: 776171 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.9151. Min Act: -0.1700

Data Index: 497342 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 3.1363. Min Range: -3.1363

Max Act: 2.8993. Min Act: -0.1700

Data Index: 186601 (C4 (Web Text))

Max Activating Token Index: 442