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

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

Neuron 746 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: 3.5845. Min Range: -3.5845

Max Act: 3.5845. Min Act: -0.1700

Data Index: 662381 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.5845. Min Act: -0.1700

Data Index: 21145 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4905. Min Act: -0.1700

Data Index: 853454 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.5062. Min Act: -0.1700

Data Index: 293368 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.5218. Min Act: -0.1700

Data Index: 1108884 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4905. Min Act: -0.1700

Data Index: 347457 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4905. Min Act: -0.1700

Data Index: 1313802 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4905. Min Act: -0.1700

Data Index: 295428 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4905. Min Act: -0.1700

Data Index: 401020 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4748. Min Act: -0.1700

Data Index: 603034 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4905. Min Act: -0.1700

Data Index: 264000 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4748. Min Act: -0.1700

Data Index: 1285746 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4592. Min Act: -0.1700

Data Index: 615218 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4121. Min Act: -0.1700

Data Index: 1040863 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4435. Min Act: -0.1700

Data Index: 676633 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4121. Min Act: -0.1700

Data Index: 1335154 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4435. Min Act: -0.1700

Data Index: 836100 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4592. Min Act: -0.1700

Data Index: 1070172 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4435. Min Act: -0.1700

Data Index: 154004 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 3.5845. Min Range: -3.5845

Max Act: 3.4748. Min Act: -0.1700

Data Index: 382479 (C4 (Web Text))

Max Activating Token Index: 844