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

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

Neuron 202 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.8842. Min Act: -0.1700

Data Index: 942045 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7591. Min Act: -0.1700

Data Index: 874038 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7434. Min Act: -0.1700

Data Index: 183271 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7121. Min Act: -0.1700

Data Index: 523724 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.6965. Min Act: -0.1700

Data Index: 914041 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.6808. Min Act: -0.1700

Data Index: 1338753 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.6965. Min Act: -0.1700

Data Index: 8490 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.6965. Min Act: -0.1700

Data Index: 1338025 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.6495. Min Act: -0.1700

Data Index: 1346243 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.6808. Min Act: -0.1700

Data Index: 892394 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.6339. Min Act: -0.1700

Data Index: 452367 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.6339. Min Act: -0.1700

Data Index: 700837 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.6026. Min Act: -0.1700

Data Index: 1039165 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.5712. Min Act: -0.1700

Data Index: 907345 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.5712. Min Act: -0.1700

Data Index: 475573 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.5712. Min Act: -0.1700

Data Index: 29513 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.5556. Min Act: -0.1700

Data Index: 1273809 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.5556. Min Act: -0.1700

Data Index: 47298 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.5556. Min Act: -0.1700

Data Index: 1017237 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.5399. Min Act: -0.1700

Data Index: 781222 (C4 (Web Text))

Max Activating Token Index: 64