Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 956 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2984. Min Act: -0.1700

Data Index: 724558 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2827. Min Act: -0.1700

Data Index: 758358 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2355. Min Act: -0.1700

Data Index: 1412889 (Python Code)

Max Activating Token Index: 852

Text #3

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2670. Min Act: -0.1700

Data Index: 1206134 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2670. Min Act: -0.1700

Data Index: 623970 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2512. Min Act: -0.1700

Data Index: 1084550 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2355. Min Act: -0.1700

Data Index: 561121 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2355. Min Act: -0.1700

Data Index: 592380 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2355. Min Act: -0.1700

Data Index: 896112 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2355. Min Act: -0.1700

Data Index: 1054016 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2355. Min Act: -0.1700

Data Index: 499264 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2198. Min Act: -0.1700

Data Index: 1179575 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2198. Min Act: -0.1700

Data Index: 681397 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2041. Min Act: -0.1700

Data Index: 375081 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2198. Min Act: -0.1700

Data Index: 452562 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2041. Min Act: -0.1700

Data Index: 325894 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.1883. Min Act: -0.1700

Data Index: 974460 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2198. Min Act: -0.1700

Data Index: 1186725 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2041. Min Act: -0.1700

Data Index: 242699 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.1726. Min Act: -0.1700

Data Index: 178754 (C4 (Web Text))

Max Activating Token Index: 787