Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1150 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.8391. Min Act: -0.1700

Data Index: 24964 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.6514. Min Act: -0.1700

Data Index: 1134533 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.6357. Min Act: -0.1700

Data Index: 862298 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.6201. Min Act: -0.1700

Data Index: 1229635 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.6201. Min Act: -0.1700

Data Index: 341557 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.5418. Min Act: -0.1700

Data Index: 1080706 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.6201. Min Act: -0.1700

Data Index: 90057 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.6044. Min Act: -0.1700

Data Index: 216291 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.5575. Min Act: -0.1700

Data Index: 513299 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.5575. Min Act: -0.1700

Data Index: 349100 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.5418. Min Act: -0.1700

Data Index: 54042 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.5105. Min Act: -0.1700

Data Index: 57350 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.5105. Min Act: -0.1700

Data Index: 337152 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.5105. Min Act: -0.1700

Data Index: 186066 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.5261. Min Act: -0.1700

Data Index: 68263 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.5105. Min Act: -0.1700

Data Index: 468716 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.4634. Min Act: -0.1700

Data Index: 693617 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.4791. Min Act: -0.1700

Data Index: 435131 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.4948. Min Act: -0.1700

Data Index: 180461 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 3.8391. Min Range: -3.8391

Max Act: 3.4634. Min Act: -0.1700

Data Index: 843332 (C4 (Web Text))

Max Activating Token Index: 751