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

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

Neuron 955 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: 3.9171. Min Range: -3.9171

Max Act: 3.9015. Min Act: -0.1699

Data Index: 933335 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.9171. Min Act: -0.1700

Data Index: 1207312 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.8546. Min Act: -0.1699

Data Index: 506800 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.8546. Min Act: -0.1700

Data Index: 927942 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.7920. Min Act: -0.1700

Data Index: 280831 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.8859. Min Act: -0.1700

Data Index: 877930 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.8546. Min Act: -0.1700

Data Index: 242439 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.7920. Min Act: -0.1700

Data Index: 919725 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.8077. Min Act: -0.1700

Data Index: 725677 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.8077. Min Act: -0.1700

Data Index: 429778 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.7920. Min Act: -0.1700

Data Index: 385442 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.7920. Min Act: -0.1697

Data Index: 217565 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.7451. Min Act: -0.1700

Data Index: 559089 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.6825. Min Act: -0.1700

Data Index: 350382 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.7295. Min Act: -0.1699

Data Index: 285414 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.6669. Min Act: -0.1700

Data Index: 460288 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.7138. Min Act: -0.1700

Data Index: 758356 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.7138. Min Act: -0.1700

Data Index: 651182 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.7451. Min Act: -0.1700

Data Index: 443863 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 3.9171. Min Range: -3.9171

Max Act: 3.7295. Min Act: -0.1700

Data Index: 870754 (C4 (Web Text))

Max Activating Token Index: 762