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

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

Neuron 1664 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: 3.6706. Min Range: -3.6706

Max Act: 3.6706. Min Act: -0.1700

Data Index: 678788 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.6706. Min Act: -0.1700

Data Index: 1145785 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.6393. Min Act: -0.1700

Data Index: 416661 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.5923. Min Act: -0.1700

Data Index: 672564 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.5297. Min Act: -0.1700

Data Index: 804867 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.4827. Min Act: -0.1700

Data Index: 1408029 (Python Code)

Max Activating Token Index: 44

Text #6

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.4983. Min Act: -0.1700

Data Index: 1168932 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.5140. Min Act: -0.1700

Data Index: 742197 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.4513. Min Act: -0.1700

Data Index: 1284487 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.4356. Min Act: -0.1700

Data Index: 749054 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.4356. Min Act: -0.1700

Data Index: 602137 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.4199. Min Act: -0.1700

Data Index: 876587 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.3572. Min Act: -0.1700

Data Index: 1106173 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.3258. Min Act: -0.1700

Data Index: 833574 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.2944. Min Act: -0.1700

Data Index: 640977 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.2787. Min Act: -0.1700

Data Index: 238703 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.2315. Min Act: -0.1700

Data Index: 337395 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.2158. Min Act: -0.1700

Data Index: 110120 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.1686. Min Act: -0.1700

Data Index: 265099 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 3.6706. Min Range: -3.6706

Max Act: 3.1843. Min Act: -0.1700

Data Index: 340431 (C4 (Web Text))

Max Activating Token Index: 398