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

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

Neuron 1469 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.5595. Min Act: -0.1700

Data Index: 1210534 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.6065. Min Act: -0.1700

Data Index: 488297 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.4812. Min Act: -0.1700

Data Index: 1151704 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.4812. Min Act: -0.1700

Data Index: 520184 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.4812. Min Act: -0.1700

Data Index: 299193 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.4185. Min Act: -0.1700

Data Index: 343883 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.3714. Min Act: -0.1700

Data Index: 871006 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.3714. Min Act: -0.1700

Data Index: 655827 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.3400. Min Act: -0.1700

Data Index: 1182187 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.3086. Min Act: -0.1700

Data Index: 801080 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.3243. Min Act: -0.1700

Data Index: 958110 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.3086. Min Act: -0.1700

Data Index: 928634 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.2929. Min Act: -0.1700

Data Index: 1019828 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.2772. Min Act: -0.1700

Data Index: 170391 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.2772. Min Act: -0.1700

Data Index: 155491 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.2772. Min Act: -0.1700

Data Index: 1232871 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.2772. Min Act: -0.1700

Data Index: 619750 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.2615. Min Act: -0.1700

Data Index: 389628 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.2458. Min Act: -0.1700

Data Index: 325799 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 3.6065. Min Range: -3.6065

Max Act: 3.2615. Min Act: -0.1700

Data Index: 677278 (C4 (Web Text))

Max Activating Token Index: 837