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

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

Neuron 1039 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: 3.8576. Min Range: -3.8576

Max Act: 3.8263. Min Act: -0.1700

Data Index: 1018742 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.8576. Min Act: -0.1700

Data Index: 927380 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7950. Min Act: -0.1700

Data Index: 1068376 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7950. Min Act: -0.1700

Data Index: 824055 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.8263. Min Act: -0.1700

Data Index: 27243 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7637. Min Act: -0.1700

Data Index: 472090 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7637. Min Act: -0.1700

Data Index: 702281 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7637. Min Act: -0.1700

Data Index: 176920 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7637. Min Act: -0.1700

Data Index: 222375 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7637. Min Act: -0.1700

Data Index: 543688 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7637. Min Act: -0.1700

Data Index: 569586 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7324. Min Act: -0.1700

Data Index: 585378 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7011. Min Act: -0.1700

Data Index: 496587 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7324. Min Act: -0.1700

Data Index: 823092 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7637. Min Act: -0.1700

Data Index: 713966 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7950. Min Act: -0.1700

Data Index: 73942 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7637. Min Act: -0.1700

Data Index: 537223 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7324. Min Act: -0.1700

Data Index: 1512392 (Python Code)

Max Activating Token Index: 668

Text #18

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7011. Min Act: -0.1700

Data Index: 1589944 (Python Code)

Max Activating Token Index: 807

Text #19

Max Range: 3.8576. Min Range: -3.8576

Max Act: 3.7324. Min Act: -0.1700

Data Index: 331979 (C4 (Web Text))

Max Activating Token Index: 511