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

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

Neuron 658 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.5534. Min Act: -0.1700

Data Index: 331399 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.5377. Min Act: -0.1700

Data Index: 962915 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.5377. Min Act: -0.1700

Data Index: 571538 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.4907. Min Act: -0.1700

Data Index: 1106905 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.4594. Min Act: -0.1700

Data Index: 222145 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.4280. Min Act: -0.1700

Data Index: 669334 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.4280. Min Act: -0.1700

Data Index: 110229 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.4437. Min Act: -0.1700

Data Index: 812581 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.4124. Min Act: -0.1700

Data Index: 1217129 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.3967. Min Act: -0.1700

Data Index: 1355856 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.3810. Min Act: -0.1700

Data Index: 998506 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.3967. Min Act: -0.1700

Data Index: 144595 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.4280. Min Act: -0.1700

Data Index: 839737 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.4124. Min Act: -0.1700

Data Index: 85375 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.3967. Min Act: -0.1700

Data Index: 581180 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.3496. Min Act: -0.1700

Data Index: 1166065 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.3653. Min Act: -0.1700

Data Index: 707805 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.4124. Min Act: -0.1700

Data Index: 483583 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.3810. Min Act: -0.1700

Data Index: 109972 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 3.5534. Min Range: -3.5534

Max Act: 3.3653. Min Act: -0.1700

Data Index: 728193 (C4 (Web Text))

Max Activating Token Index: 960