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

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

Neuron 670 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1628. Min Range: -3.1628

Max Act: 3.1628. Min Act: -0.1700

Data Index: 207085 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 3.1628. Min Range: -3.1628

Max Act: 3.0682. Min Act: -0.1700

Data Index: 311754 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 3.1628. Min Range: -3.1628

Max Act: 3.0524. Min Act: -0.1700

Data Index: 54154 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.9734. Min Act: -0.1700

Data Index: 894585 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.9576. Min Act: -0.1700

Data Index: 174879 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.9417. Min Act: -0.1700

Data Index: 753212 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.9259. Min Act: -0.1700

Data Index: 1107493 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.9417. Min Act: -0.1700

Data Index: 280385 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.9259. Min Act: -0.1700

Data Index: 1018845 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.9259. Min Act: -0.1700

Data Index: 1317210 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.9100. Min Act: -0.1700

Data Index: 1001794 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.8783. Min Act: -0.1700

Data Index: 517969 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.8783. Min Act: -0.1700

Data Index: 1349147 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.8942. Min Act: -0.1700

Data Index: 280440 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.8783. Min Act: -0.1700

Data Index: 933667 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.8783. Min Act: -0.1700

Data Index: 672642 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.8624. Min Act: -0.1700

Data Index: 1155295 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.8624. Min Act: -0.1700

Data Index: 1147798 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.8306. Min Act: -0.1700

Data Index: 1344985 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 3.1628. Min Range: -3.1628

Max Act: 2.8465. Min Act: -0.1700

Data Index: 653113 (C4 (Web Text))

Max Activating Token Index: 278