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

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

Neuron 816 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: 5.8553. Min Range: -5.8553

Max Act: 5.8553. Min Act: -0.1700

Data Index: 759808 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.9803. Min Act: -0.1700

Data Index: 1034012 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.7928. Min Act: -0.1700

Data Index: 173801 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.7615. Min Act: -0.1700

Data Index: 898597 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.7615. Min Act: -0.1700

Data Index: 1226058 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.6990. Min Act: -0.1700

Data Index: 1353229 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.6677. Min Act: -0.1700

Data Index: 103587 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.6990. Min Act: -0.1700

Data Index: 67865 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.6677. Min Act: -0.1700

Data Index: 8876 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.6365. Min Act: -0.1700

Data Index: 1077060 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.6052. Min Act: -0.1700

Data Index: 566259 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.6052. Min Act: -0.1700

Data Index: 1323048 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.6052. Min Act: -0.1700

Data Index: 1327277 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.5740. Min Act: -0.1700

Data Index: 1616591 (Python Code)

Max Activating Token Index: 961

Text #14

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.5740. Min Act: -0.1700

Data Index: 215592 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.5427. Min Act: -0.1700

Data Index: 789694 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.5427. Min Act: -0.1700

Data Index: 367888 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.5427. Min Act: -0.1700

Data Index: 269847 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.5115. Min Act: -0.1700

Data Index: 253209 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 5.8553. Min Range: -5.8553

Max Act: 4.5115. Min Act: -0.1700

Data Index: 416300 (C4 (Web Text))

Max Activating Token Index: 121