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

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

Neuron 388 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.7481. Min Act: -0.1700

Data Index: 1144378 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.5919. Min Act: -0.1700

Data Index: 191988 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.5606. Min Act: -0.1700

Data Index: 1160003 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.4356. Min Act: -0.1700

Data Index: 596070 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.3731. Min Act: -0.1672

Data Index: 480449 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.4044. Min Act: -0.1700

Data Index: 1025412 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.4044. Min Act: -0.1700

Data Index: 1315581 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.4044. Min Act: -0.1700

Data Index: 1186994 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.3731. Min Act: -0.1700

Data Index: 418397 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.3106. Min Act: -0.1700

Data Index: 943133 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.3106. Min Act: -0.1700

Data Index: 872923 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.3106. Min Act: -0.1700

Data Index: 717620 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.2481. Min Act: -0.1700

Data Index: 721524 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.2794. Min Act: -0.1700

Data Index: 980520 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.2794. Min Act: -0.1700

Data Index: 1038585 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.2794. Min Act: -0.1699

Data Index: 144082 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.2481. Min Act: -0.1700

Data Index: 1212194 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.2481. Min Act: -0.1700

Data Index: 1100101 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.2169. Min Act: -0.1700

Data Index: 191484 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.1856. Min Act: -0.1700

Data Index: 428773 (C4 (Web Text))

Max Activating Token Index: 667