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

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

Neuron 1549 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.6590. Min Act: -0.1700

Data Index: 701285 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.4402. Min Act: -0.1700

Data Index: 86694 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.3465. Min Act: -0.1700

Data Index: 712916 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.3777. Min Act: -0.1700

Data Index: 892284 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.3152. Min Act: -0.1700

Data Index: 223816 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.2527. Min Act: -0.1700

Data Index: 944131 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.3152. Min Act: -0.1700

Data Index: 703340 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.2527. Min Act: -0.1700

Data Index: 1149787 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.2840. Min Act: -0.1700

Data Index: 1268863 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.2840. Min Act: -0.1700

Data Index: 732026 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.2527. Min Act: -0.1700

Data Index: 1249636 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.2215. Min Act: -0.1700

Data Index: 674053 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.2215. Min Act: -0.1700

Data Index: 184789 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.1902. Min Act: -0.1700

Data Index: 612872 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.2527. Min Act: -0.1700

Data Index: 122211 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.2215. Min Act: -0.1700

Data Index: 677909 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.2527. Min Act: -0.1700

Data Index: 1109169 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.1902. Min Act: -0.1700

Data Index: 1249354 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.1590. Min Act: -0.1700

Data Index: 980251 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 5.6590. Min Range: -5.6590

Max Act: 5.2527. Min Act: -0.1700

Data Index: 1095222 (C4 (Web Text))

Max Activating Token Index: 993