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

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

Neuron 196 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: 3.2644. Min Range: -3.2644

Max Act: 3.2644. Min Act: -0.1700

Data Index: 1106975 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.1439. Min Act: -0.1700

Data Index: 391121 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.1323. Min Act: -0.1700

Data Index: 373620 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.1110. Min Act: -0.1700

Data Index: 1195464 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.1047. Min Act: -0.1700

Data Index: 692407 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0959. Min Act: -0.1700

Data Index: 102558 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0671. Min Act: -0.1700

Data Index: 676391 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0503. Min Act: -0.1700

Data Index: 74585 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0551. Min Act: -0.1700

Data Index: 475623 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0468. Min Act: -0.1700

Data Index: 497944 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0503. Min Act: -0.1700

Data Index: 262049 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0441. Min Act: -0.1700

Data Index: 1185384 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0153. Min Act: -0.1700

Data Index: 729593 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0286. Min Act: -0.1700

Data Index: 1101322 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0140. Min Act: -0.1700

Data Index: 1252843 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0117. Min Act: -0.1700

Data Index: 268254 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 3.2644. Min Range: -3.2644

Max Act: 2.9970. Min Act: -0.1700

Data Index: 582800 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0122. Min Act: -0.1700

Data Index: 857768 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0103. Min Act: -0.1700

Data Index: 274947 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 3.2644. Min Range: -3.2644

Max Act: 3.0099. Min Act: -0.1700

Data Index: 196287 (C4 (Web Text))

Max Activating Token Index: 247