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

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

Neuron 273 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.4249. Min Act: -0.1700

Data Index: 1128855 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.3936. Min Act: -0.1700

Data Index: 349863 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.3936. Min Act: -0.1700

Data Index: 211769 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.3308. Min Act: -0.1700

Data Index: 666820 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.3622. Min Act: -0.1700

Data Index: 754991 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.3622. Min Act: -0.1700

Data Index: 595296 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.3622. Min Act: -0.1700

Data Index: 1359466 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2994. Min Act: -0.1700

Data Index: 110893 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2994. Min Act: -0.1700

Data Index: 967706 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2680. Min Act: -0.1700

Data Index: 952666 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2680. Min Act: -0.1700

Data Index: 1330053 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2680. Min Act: -0.1700

Data Index: 1002081 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2680. Min Act: -0.1700

Data Index: 576033 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2680. Min Act: -0.1700

Data Index: 1049798 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2680. Min Act: -0.1700

Data Index: 1288918 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2680. Min Act: -0.1700

Data Index: 304511 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2365. Min Act: -0.1700

Data Index: 1095576 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2208. Min Act: -0.1700

Data Index: 15581 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2680. Min Act: -0.1700

Data Index: 929439 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2208. Min Act: -0.1700

Data Index: 786740 (C4 (Web Text))

Max Activating Token Index: 503