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

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

Neuron 653 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.3784. Min Act: -0.1700

Data Index: 408124 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.3314. Min Act: -0.1700

Data Index: 1102408 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.3157. Min Act: -0.1700

Data Index: 472490 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.3000. Min Act: -0.1700

Data Index: 846878 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.2685. Min Act: -0.1700

Data Index: 26375 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.2528. Min Act: -0.1700

Data Index: 787037 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.2214. Min Act: -0.1700

Data Index: 68267 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.2214. Min Act: -0.1700

Data Index: 423514 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.1899. Min Act: -0.1700

Data Index: 1123858 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.1742. Min Act: -0.1700

Data Index: 384038 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.1899. Min Act: -0.1700

Data Index: 328063 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.1899. Min Act: -0.1700

Data Index: 1112925 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.1742. Min Act: -0.1700

Data Index: 607491 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.1584. Min Act: -0.1700

Data Index: 567388 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.1584. Min Act: -0.1700

Data Index: 1160405 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.1584. Min Act: -0.1700

Data Index: 265373 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.1427. Min Act: -0.1700

Data Index: 934460 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.1269. Min Act: -0.1700

Data Index: 702245 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.1269. Min Act: -0.1700

Data Index: 1230551 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 3.3784. Min Range: -3.3784

Max Act: 3.1269. Min Act: -0.1700

Data Index: 822525 (C4 (Web Text))

Max Activating Token Index: 987