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

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

Neuron 1299 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0517. Min Range: -3.0517

Max Act: 3.0517. Min Act: -0.1700

Data Index: 345878 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9410. Min Act: -0.1700

Data Index: 959113 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9410. Min Act: -0.1700

Data Index: 823205 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9726. Min Act: -0.1700

Data Index: 838458 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9568. Min Act: -0.1700

Data Index: 982961 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9093. Min Act: -0.1700

Data Index: 86484 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9251. Min Act: -0.1700

Data Index: 968301 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.8934. Min Act: -0.1700

Data Index: 398634 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.8775. Min Act: -0.1700

Data Index: 465185 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.8617. Min Act: -0.1700

Data Index: 652321 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.8617. Min Act: -0.1700

Data Index: 249617 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.8934. Min Act: -0.1700

Data Index: 217169 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.8458. Min Act: -0.1700

Data Index: 827102 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.8617. Min Act: -0.1700

Data Index: 1067654 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.8458. Min Act: -0.1700

Data Index: 928446 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.7821. Min Act: -0.1700

Data Index: 1293231 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.8617. Min Act: -0.1700

Data Index: 1090881 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.7980. Min Act: -0.1700

Data Index: 815661 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.7980. Min Act: -0.1700

Data Index: 560379 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.7502. Min Act: -0.1700

Data Index: 269463 (C4 (Web Text))

Max Activating Token Index: 868