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

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

Neuron 1847 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: 3.1499. Min Range: -3.1499

Max Act: 3.1499. Min Act: -0.1700

Data Index: 370572 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.1499. Min Act: -0.1700

Data Index: 421053 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.1341. Min Act: -0.1700

Data Index: 873153 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.1026. Min Act: -0.1700

Data Index: 111139 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0868. Min Act: -0.1700

Data Index: 954210 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0711. Min Act: -0.1700

Data Index: 242320 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.1026. Min Act: -0.1700

Data Index: 513289 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0868. Min Act: -0.1700

Data Index: 69978 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0395. Min Act: -0.1700

Data Index: 1508086 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0395. Min Act: -0.1700

Data Index: 1651604 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0395. Min Act: -0.1700

Data Index: 5491 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0395. Min Act: -0.1700

Data Index: 168139 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0395. Min Act: -0.1700

Data Index: 129787 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0237. Min Act: -0.1700

Data Index: 774151 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0079. Min Act: -0.1700

Data Index: 172310 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0237. Min Act: -0.1700

Data Index: 824881 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0237. Min Act: -0.1700

Data Index: 75944 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0237. Min Act: -0.1700

Data Index: 561527 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.0079. Min Act: -0.1700

Data Index: 751040 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.9763. Min Act: -0.1700

Data Index: 1565618 (Python Code)

Max Activating Token Index: 174