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

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

Neuron 581 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: 3.8854. Min Range: -3.8854

Max Act: 3.8698. Min Act: -0.1700

Data Index: 1048823 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8698. Min Act: -0.1700

Data Index: 189379 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8542. Min Act: -0.1700

Data Index: 214152 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8385. Min Act: -0.1700

Data Index: 937179 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8542. Min Act: -0.1700

Data Index: 822313 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8854. Min Act: -0.1700

Data Index: 215882 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8229. Min Act: -0.1700

Data Index: 485348 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8229. Min Act: -0.1700

Data Index: 1008662 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8385. Min Act: -0.1700

Data Index: 327362 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8385. Min Act: -0.1700

Data Index: 452190 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8385. Min Act: -0.1700

Data Index: 411856 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8073. Min Act: -0.1700

Data Index: 1068348 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8385. Min Act: -0.1700

Data Index: 1247001 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8229. Min Act: -0.1700

Data Index: 742152 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8073. Min Act: -0.1700

Data Index: 1041580 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8385. Min Act: -0.1700

Data Index: 211660 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8229. Min Act: -0.1700

Data Index: 463898 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8229. Min Act: -0.1700

Data Index: 186390 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8229. Min Act: -0.1700

Data Index: 1120519 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 3.8854. Min Range: -3.8854

Max Act: 3.8229. Min Act: -0.1700

Data Index: 697965 (C4 (Web Text))

Max Activating Token Index: 11