Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 821 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.3444. Min Act: -0.1700

Data Index: 804312 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.0319. Min Act: -0.1700

Data Index: 574795 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.8756. Min Act: -0.1700

Data Index: 216244 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.8131. Min Act: -0.1700

Data Index: 980069 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.8131. Min Act: -0.1700

Data Index: 514946 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.6881. Min Act: -0.1700

Data Index: 784455 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.6569. Min Act: -0.1700

Data Index: 1334659 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.6569. Min Act: -0.1700

Data Index: 1006753 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.5631. Min Act: -0.1700

Data Index: 1296819 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.5319. Min Act: -0.1700

Data Index: 437131 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.4694. Min Act: -0.1700

Data Index: 1287078 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.4694. Min Act: -0.1700

Data Index: 929616 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.5006. Min Act: -0.1700

Data Index: 995010 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.5319. Min Act: -0.1700

Data Index: 572827 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.5006. Min Act: -0.1700

Data Index: 1091258 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.4694. Min Act: -0.1700

Data Index: 510681 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.4694. Min Act: -0.1700

Data Index: 285750 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.3756. Min Act: -0.1700

Data Index: 479474 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.4381. Min Act: -0.1700

Data Index: 962133 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.4694. Min Act: -0.1700

Data Index: 428200 (C4 (Web Text))

Max Activating Token Index: 210