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

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

Neuron 1871 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: 3.3155. Min Range: -3.3155

Max Act: 3.3155. Min Act: -0.1700

Data Index: 584549 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2527. Min Act: -0.1700

Data Index: 118438 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2527. Min Act: -0.1700

Data Index: 648548 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2527. Min Act: -0.1700

Data Index: 621533 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2213. Min Act: -0.1700

Data Index: 1283007 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2213. Min Act: -0.1700

Data Index: 138009 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2213. Min Act: -0.1700

Data Index: 1112033 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2213. Min Act: -0.1700

Data Index: 1020623 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2055. Min Act: -0.1700

Data Index: 973179 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2213. Min Act: -0.1700

Data Index: 602439 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2213. Min Act: -0.1700

Data Index: 944531 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2055. Min Act: -0.1700

Data Index: 234088 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2055. Min Act: -0.1700

Data Index: 887611 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.1898. Min Act: -0.1700

Data Index: 1254202 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2055. Min Act: -0.1700

Data Index: 794254 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2055. Min Act: -0.1700

Data Index: 678376 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2055. Min Act: -0.1700

Data Index: 371034 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2055. Min Act: -0.1700

Data Index: 429615 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2055. Min Act: -0.1700

Data Index: 242757 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2213. Min Act: -0.1700

Data Index: 45474 (C4 (Web Text))

Max Activating Token Index: 410