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

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

Neuron 1679 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: 3.4574. Min Range: -3.4574

Max Act: 3.4574. Min Act: -0.1700

Data Index: 1019455 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.4103. Min Act: -0.1700

Data Index: 948569 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.4103. Min Act: -0.1700

Data Index: 488574 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.4103. Min Act: -0.1700

Data Index: 777296 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.4260. Min Act: -0.1700

Data Index: 1148580 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3946. Min Act: -0.1700

Data Index: 1272105 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3789. Min Act: -0.1700

Data Index: 837119 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3789. Min Act: -0.1700

Data Index: 1034526 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3633. Min Act: -0.1700

Data Index: 459604 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3789. Min Act: -0.1700

Data Index: 431834 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3789. Min Act: -0.1700

Data Index: 684789 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3789. Min Act: -0.1700

Data Index: 98391 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3476. Min Act: -0.1700

Data Index: 966908 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3319. Min Act: -0.1700

Data Index: 689410 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3633. Min Act: -0.1700

Data Index: 1019196 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3476. Min Act: -0.1700

Data Index: 214968 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3476. Min Act: -0.1700

Data Index: 1030734 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3162. Min Act: -0.1700

Data Index: 981872 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3319. Min Act: -0.1700

Data Index: 273792 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 3.4574. Min Range: -3.4574

Max Act: 3.3319. Min Act: -0.1700

Data Index: 495959 (C4 (Web Text))

Max Activating Token Index: 753