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

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

Neuron 411 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: 5.6546. Min Range: -5.6546

Max Act: 5.5608. Min Act: -0.1700

Data Index: 1331181 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.6546. Min Act: -0.1700

Data Index: 338594 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.5608. Min Act: -0.1700

Data Index: 550222 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.5296. Min Act: -0.1700

Data Index: 796384 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.6233. Min Act: -0.1700

Data Index: 1229127 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.4983. Min Act: -0.1700

Data Index: 938405 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.5296. Min Act: -0.1700

Data Index: 353105 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.5296. Min Act: -0.1700

Data Index: 1261488 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.4671. Min Act: -0.1700

Data Index: 576924 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.5296. Min Act: -0.1700

Data Index: 92426 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.3421. Min Act: -0.1700

Data Index: 755615 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.3421. Min Act: -0.1700

Data Index: 1078669 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.3421. Min Act: -0.1700

Data Index: 564722 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.4046. Min Act: -0.1700

Data Index: 1035191 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.3421. Min Act: -0.1700

Data Index: 896251 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.4046. Min Act: -0.1700

Data Index: 1150058 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.3421. Min Act: -0.1700

Data Index: 183858 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.2483. Min Act: -0.1700

Data Index: 702716 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.3108. Min Act: -0.1700

Data Index: 919775 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 5.6546. Min Range: -5.6546

Max Act: 5.3108. Min Act: -0.1700

Data Index: 417795 (C4 (Web Text))

Max Activating Token Index: 740