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

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

Neuron 528 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: 5.0706. Min Range: -5.0706

Max Act: 5.0706. Min Act: -0.1700

Data Index: 953539 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 5.0706. Min Range: -5.0706

Max Act: 5.0393. Min Act: -0.1700

Data Index: 935238 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 5.0706. Min Range: -5.0706

Max Act: 5.0081. Min Act: -0.1700

Data Index: 221188 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.9768. Min Act: -0.1700

Data Index: 113792 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.8674. Min Act: -0.1700

Data Index: 1144595 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.9299. Min Act: -0.1700

Data Index: 576977 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.9924. Min Act: -0.1700

Data Index: 1116053 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.9612. Min Act: -0.1700

Data Index: 807407 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.9456. Min Act: -0.1700

Data Index: 666236 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.8831. Min Act: -0.1700

Data Index: 550745 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.9456. Min Act: -0.1700

Data Index: 603273 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.8674. Min Act: -0.1700

Data Index: 1230848 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.9924. Min Act: -0.1700

Data Index: 1062303 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.8362. Min Act: -0.1700

Data Index: 750668 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.8674. Min Act: -0.1700

Data Index: 1280657 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.8362. Min Act: -0.1700

Data Index: 451902 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.8362. Min Act: -0.1700

Data Index: 330025 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.8049. Min Act: -0.1700

Data Index: 1004919 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.8206. Min Act: -0.1700

Data Index: 527633 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 5.0706. Min Range: -5.0706

Max Act: 4.7893. Min Act: -0.1700

Data Index: 467793 (C4 (Web Text))

Max Activating Token Index: 924