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

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

Neuron 1709 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: 3.4676. Min Range: -3.4676

Max Act: 3.4676. Min Act: -0.1700

Data Index: 541267 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.4362. Min Act: -0.1700

Data Index: 966277 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.3735. Min Act: -0.1700

Data Index: 276500 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.3107. Min Act: -0.1700

Data Index: 554667 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.2950. Min Act: -0.1700

Data Index: 437942 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.2950. Min Act: -0.1700

Data Index: 285123 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.2478. Min Act: -0.1700

Data Index: 1147576 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.2321. Min Act: -0.1700

Data Index: 829812 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.2321. Min Act: -0.1700

Data Index: 981339 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.2478. Min Act: -0.1700

Data Index: 467500 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.2007. Min Act: -0.1700

Data Index: 1055515 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.2164. Min Act: -0.1700

Data Index: 1023604 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.1534. Min Act: -0.1700

Data Index: 669971 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.1692. Min Act: -0.1700

Data Index: 1237210 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.2164. Min Act: -0.1700

Data Index: 1140273 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.2478. Min Act: -0.1700

Data Index: 561635 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.2164. Min Act: -0.1700

Data Index: 183743 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.1534. Min Act: -0.1700

Data Index: 455485 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.1849. Min Act: -0.1700

Data Index: 308299 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 3.4676. Min Range: -3.4676

Max Act: 3.1534. Min Act: -0.1700

Data Index: 869445 (C4 (Web Text))

Max Activating Token Index: 813