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

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

Neuron 829 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: 3.1691. Min Range: -3.1691

Max Act: 3.1691. Min Act: -0.1700

Data Index: 10565 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 3.1691. Min Range: -3.1691

Max Act: 3.1079. Min Act: -0.1700

Data Index: 574433 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 3.1691. Min Range: -3.1691

Max Act: 3.1032. Min Act: -0.1700

Data Index: 418519 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 3.1691. Min Range: -3.1691

Max Act: 3.0522. Min Act: -0.1700

Data Index: 1294051 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 3.1691. Min Range: -3.1691

Max Act: 3.0180. Min Act: -0.1700

Data Index: 473876 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 3.1691. Min Range: -3.1691

Max Act: 3.0220. Min Act: -0.1700

Data Index: 63991 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 3.1691. Min Range: -3.1691

Max Act: 2.9511. Min Act: -0.1700

Data Index: 96842 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 3.1691. Min Range: -3.1691

Max Act: 3.0128. Min Act: -0.1700

Data Index: 1083779 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 3.1691. Min Range: -3.1691

Max Act: 2.9989. Min Act: -0.1700

Data Index: 464608 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 3.1691. Min Range: -3.1691

Max Act: 2.9919. Min Act: -0.1700

Data Index: 175242 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 3.1691. Min Range: -3.1691

Max Act: 2.9939. Min Act: -0.1700

Data Index: 174241 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 3.1691. Min Range: -3.1691

Max Act: 2.9910. Min Act: -0.1700

Data Index: 328914 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 3.1691. Min Range: -3.1691

Max Act: 3.0126. Min Act: -0.1700

Data Index: 312505 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 3.1691. Min Range: -3.1691

Max Act: 2.9987. Min Act: -0.1700

Data Index: 458285 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 3.1691. Min Range: -3.1691

Max Act: 2.9895. Min Act: -0.1700

Data Index: 347737 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 3.1691. Min Range: -3.1691

Max Act: 3.0177. Min Act: -0.1700

Data Index: 1151474 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 3.1691. Min Range: -3.1691

Max Act: 2.9129. Min Act: -0.1700

Data Index: 1086470 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 3.1691. Min Range: -3.1691

Max Act: 2.9713. Min Act: -0.1700

Data Index: 980635 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 3.1691. Min Range: -3.1691

Max Act: 2.9066. Min Act: -0.1700

Data Index: 1176386 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 3.1691. Min Range: -3.1691

Max Act: 2.9552. Min Act: -0.1700

Data Index: 1199628 (C4 (Web Text))

Max Activating Token Index: 404