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

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

Neuron 1283 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: 3.8392. Min Range: -3.8392

Max Act: 3.8079. Min Act: -0.1700

Data Index: 312234 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.8392. Min Act: -0.1700

Data Index: 1346208 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.8079. Min Act: -0.1700

Data Index: 1231520 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.8392. Min Act: -0.1700

Data Index: 122502 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.8392. Min Act: -0.1700

Data Index: 978616 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7610. Min Act: -0.1700

Data Index: 1283325 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7922. Min Act: -0.1700

Data Index: 590413 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7610. Min Act: -0.1700

Data Index: 1007380 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.8392. Min Act: -0.1700

Data Index: 741925 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7922. Min Act: -0.1700

Data Index: 1353576 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7922. Min Act: -0.1700

Data Index: 1079810 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7922. Min Act: -0.1700

Data Index: 27834 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7453. Min Act: -0.1700

Data Index: 879912 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7610. Min Act: -0.1700

Data Index: 83868 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7453. Min Act: -0.1700

Data Index: 197910 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7922. Min Act: -0.1700

Data Index: 332578 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.6984. Min Act: -0.1700

Data Index: 627834 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7297. Min Act: -0.1700

Data Index: 309803 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.6671. Min Act: -0.1700

Data Index: 785907 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.6984. Min Act: -0.1700

Data Index: 260334 (C4 (Web Text))

Max Activating Token Index: 559