Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 599 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.3115. Min Act: -0.1700

Data Index: 254351 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.2649. Min Act: -0.1700

Data Index: 446419 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.2703. Min Act: -0.1700

Data Index: 483316 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.2298. Min Act: -0.1700

Data Index: 586602 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.2121. Min Act: -0.1700

Data Index: 111683 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1827. Min Act: -0.1700

Data Index: 289668 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1814. Min Act: -0.1700

Data Index: 761367 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1949. Min Act: -0.1700

Data Index: 665292 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1822. Min Act: -0.1700

Data Index: 1143517 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1788. Min Act: -0.1700

Data Index: 514851 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1892. Min Act: -0.1700

Data Index: 129332 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1451. Min Act: -0.1700

Data Index: 603471 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1875. Min Act: -0.1700

Data Index: 596463 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1392. Min Act: -0.1700

Data Index: 634476 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1321. Min Act: -0.1700

Data Index: 69440 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1225. Min Act: -0.1700

Data Index: 652397 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1078. Min Act: -0.1700

Data Index: 423903 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1621. Min Act: -0.1700

Data Index: 974795 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1332. Min Act: -0.1700

Data Index: 244099 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 4.3115. Min Range: -4.3115

Max Act: 4.1002. Min Act: -0.1700

Data Index: 289272 (C4 (Web Text))

Max Activating Token Index: 654