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

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

Neuron 1640 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.3032. Min Act: -0.1700

Data Index: 1198279 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.3344. Min Act: -0.1700

Data Index: 469694 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.2094. Min Act: -0.1700

Data Index: 800120 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.2407. Min Act: -0.1700

Data Index: 1199911 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.2094. Min Act: -0.1700

Data Index: 1097708 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.1469. Min Act: -0.1700

Data Index: 1342621 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.1469. Min Act: -0.1700

Data Index: 713984 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.0532. Min Act: -0.1700

Data Index: 112221 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.0844. Min Act: -0.1700

Data Index: 61517 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.1157. Min Act: -0.1700

Data Index: 828778 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.1157. Min Act: -0.1700

Data Index: 498952 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.0532. Min Act: -0.1700

Data Index: 993660 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.0844. Min Act: -0.1700

Data Index: 115121 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.0219. Min Act: -0.1700

Data Index: 418041 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.1157. Min Act: -0.1700

Data Index: 1289469 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.0532. Min Act: -0.1700

Data Index: 248145 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 5.3344. Min Range: -5.3344

Max Act: 4.9907. Min Act: -0.1700

Data Index: 187141 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 5.3344. Min Range: -5.3344

Max Act: 4.9907. Min Act: -0.1700

Data Index: 25663 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.0219. Min Act: -0.1700

Data Index: 629967 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 5.3344. Min Range: -5.3344

Max Act: 5.0219. Min Act: -0.1700

Data Index: 1236517 (C4 (Web Text))

Max Activating Token Index: 833