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

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

Neuron 393 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.3259. Min Act: -0.1700

Data Index: 633315 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.3259. Min Act: -0.1700

Data Index: 1282528 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.3259. Min Act: -0.1700

Data Index: 382873 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.3102. Min Act: -0.1700

Data Index: 1337402 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2788. Min Act: -0.1700

Data Index: 453197 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2945. Min Act: -0.1700

Data Index: 219492 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2945. Min Act: -0.1700

Data Index: 371449 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2631. Min Act: -0.1700

Data Index: 1299460 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2788. Min Act: -0.1700

Data Index: 740700 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2788. Min Act: -0.1700

Data Index: 898990 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2631. Min Act: -0.1700

Data Index: 99809 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2474. Min Act: -0.1700

Data Index: 1206354 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2945. Min Act: -0.1700

Data Index: 578179 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2631. Min Act: -0.1700

Data Index: 746147 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2788. Min Act: -0.1700

Data Index: 193015 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.3102. Min Act: -0.1700

Data Index: 240973 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2945. Min Act: -0.1700

Data Index: 289307 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2631. Min Act: -0.1700

Data Index: 1035015 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2631. Min Act: -0.1700

Data Index: 1001284 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 3.3259. Min Range: -3.3259

Max Act: 3.2631. Min Act: -0.1700

Data Index: 658696 (C4 (Web Text))

Max Activating Token Index: 33