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

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

Neuron 325 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.8461. Min Act: -0.1700

Data Index: 1126616 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.6586. Min Act: -0.1700

Data Index: 354748 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.7211. Min Act: -0.1700

Data Index: 1009268 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.5961. Min Act: -0.1700

Data Index: 589963 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.6899. Min Act: -0.1700

Data Index: 1240529 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.6899. Min Act: -0.1700

Data Index: 1169225 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.6274. Min Act: -0.1700

Data Index: 52036 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.6274. Min Act: -0.1700

Data Index: 557500 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.5336. Min Act: -0.1700

Data Index: 922619 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.5024. Min Act: -0.1700

Data Index: 327203 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.5024. Min Act: -0.1700

Data Index: 846140 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.5649. Min Act: -0.1700

Data Index: 341683 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.5336. Min Act: -0.1700

Data Index: 272216 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.5024. Min Act: -0.1700

Data Index: 42614 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.5024. Min Act: -0.1700

Data Index: 535600 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.5649. Min Act: -0.1700

Data Index: 1297547 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.5024. Min Act: -0.1700

Data Index: 58214 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.5336. Min Act: -0.1700

Data Index: 1283629 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.4711. Min Act: -0.1700

Data Index: 1250956 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 5.8461. Min Range: -5.8461

Max Act: 5.3774. Min Act: -0.1700

Data Index: 303306 (C4 (Web Text))

Max Activating Token Index: 318