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

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

Neuron 1054 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.2185. Min Act: -0.1700

Data Index: 842493 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.2498. Min Act: -0.1700

Data Index: 525785 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.2498. Min Act: -0.1700

Data Index: 259802 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.2498. Min Act: -0.1700

Data Index: 741456 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.1873. Min Act: -0.1700

Data Index: 576184 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.1873. Min Act: -0.1700

Data Index: 1088893 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.1560. Min Act: -0.1700

Data Index: 1021316 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.2185. Min Act: -0.1700

Data Index: 267363 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.1873. Min Act: -0.1700

Data Index: 442225 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.1560. Min Act: -0.1700

Data Index: 115379 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.1248. Min Act: -0.1700

Data Index: 302996 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.1560. Min Act: -0.1700

Data Index: 972584 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.1560. Min Act: -0.1700

Data Index: 683447 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.2185. Min Act: -0.1700

Data Index: 53467 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.1248. Min Act: -0.1700

Data Index: 557801 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.1560. Min Act: -0.1700

Data Index: 50445 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.1248. Min Act: -0.1700

Data Index: 382967 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.0935. Min Act: -0.1700

Data Index: 317558 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.2498. Min Act: -0.1700

Data Index: 731269 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 5.2498. Min Range: -5.2498

Max Act: 5.2185. Min Act: -0.1700

Data Index: 383113 (C4 (Web Text))

Max Activating Token Index: 161