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

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

Neuron 1954 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.5720. Min Act: -0.1700

Data Index: 1297549 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.5094. Min Act: -0.1700

Data Index: 1258813 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.4937. Min Act: -0.1700

Data Index: 950728 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.5094. Min Act: -0.1700

Data Index: 696827 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.4780. Min Act: -0.1700

Data Index: 853237 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.4624. Min Act: -0.1700

Data Index: 132456 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.4467. Min Act: -0.1700

Data Index: 884708 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.4780. Min Act: -0.1700

Data Index: 1280708 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.4467. Min Act: -0.1700

Data Index: 450191 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.4467. Min Act: -0.1700

Data Index: 110253 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.4624. Min Act: -0.1700

Data Index: 988570 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.4310. Min Act: -0.1700

Data Index: 1019135 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.4310. Min Act: -0.1700

Data Index: 853454 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.3996. Min Act: -0.1700

Data Index: 689022 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.3840. Min Act: -0.1700

Data Index: 858356 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.3996. Min Act: -0.1700

Data Index: 656750 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.4153. Min Act: -0.1700

Data Index: 299618 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.3840. Min Act: -0.1700

Data Index: 1021893 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.3840. Min Act: -0.1700

Data Index: 377515 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 3.5720. Min Range: -3.5720

Max Act: 3.3996. Min Act: -0.1700

Data Index: 1001245 (C4 (Web Text))

Max Activating Token Index: 887