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

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

Neuron 880 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.4447. Min Act: -0.1700

Data Index: 1195606 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3820. Min Act: -0.1700

Data Index: 326033 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3977. Min Act: -0.1700

Data Index: 891956 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3977. Min Act: -0.1700

Data Index: 74530 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3820. Min Act: -0.1700

Data Index: 703380 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3820. Min Act: -0.1700

Data Index: 273365 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3663. Min Act: -0.1700

Data Index: 671628 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3820. Min Act: -0.1700

Data Index: 301527 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3977. Min Act: -0.1700

Data Index: 24683 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3663. Min Act: -0.1700

Data Index: 1593221 (Python Code)

Max Activating Token Index: 630

Text #10

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3663. Min Act: -0.1700

Data Index: 1105245 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3663. Min Act: -0.1700

Data Index: 1277226 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3506. Min Act: -0.1700

Data Index: 1303148 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3349. Min Act: -0.1700

Data Index: 364623 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3349. Min Act: -0.1700

Data Index: 678841 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3349. Min Act: -0.1700

Data Index: 488997 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3349. Min Act: -0.1700

Data Index: 1321091 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3506. Min Act: -0.1700

Data Index: 1371929 (Python Code)

Max Activating Token Index: 948

Text #18

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3192. Min Act: -0.1700

Data Index: 1174072 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 3.4447. Min Range: -3.4447

Max Act: 3.3192. Min Act: -0.1700

Data Index: 1241373 (C4 (Web Text))

Max Activating Token Index: 962