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

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

Neuron 988 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.4301. Min Act: -0.1700

Data Index: 307035 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.2732. Min Act: -0.1700

Data Index: 1042662 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.3046. Min Act: -0.1700

Data Index: 1225762 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.3046. Min Act: -0.1700

Data Index: 1066801 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.2417. Min Act: -0.1700

Data Index: 867480 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.2103. Min Act: -0.1700

Data Index: 6286 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.1473. Min Act: -0.1700

Data Index: 177883 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.1788. Min Act: -0.1700

Data Index: 790566 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 3.4301. Min Range: -3.4301

Max Act: 2.9262. Min Act: -0.1700

Data Index: 738942 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.2732. Min Act: -0.1700

Data Index: 1199070 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.1788. Min Act: -0.1700

Data Index: 23836 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.1788. Min Act: -0.1700

Data Index: 1316162 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 3.4301. Min Range: -3.4301

Max Act: 2.9737. Min Act: -0.1700

Data Index: 418170 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.1788. Min Act: -0.1700

Data Index: 636879 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.1158. Min Act: -0.1700

Data Index: 1083075 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.1788. Min Act: -0.1700

Data Index: 767262 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.1158. Min Act: -0.1700

Data Index: 1023935 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.0685. Min Act: -0.1700

Data Index: 901388 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.1473. Min Act: -0.1700

Data Index: 111840 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 3.4301. Min Range: -3.4301

Max Act: 3.1788. Min Act: -0.1700

Data Index: 687787 (C4 (Web Text))

Max Activating Token Index: 538