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

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

Neuron 1827 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4218. Min Range: -5.4218

Max Act: 5.4218. Min Act: -0.1700

Data Index: 573779 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 5.4218. Min Range: -5.4218

Max Act: 5.2030. Min Act: -0.1700

Data Index: 781279 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 5.4218. Min Range: -5.4218

Max Act: 5.1093. Min Act: -0.1700

Data Index: 784940 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 5.4218. Min Range: -5.4218

Max Act: 5.0780. Min Act: -0.1700

Data Index: 173922 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 5.4218. Min Range: -5.4218

Max Act: 5.0780. Min Act: -0.1700

Data Index: 1059994 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 5.4218. Min Range: -5.4218

Max Act: 5.0780. Min Act: -0.1700

Data Index: 1710 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 5.4218. Min Range: -5.4218

Max Act: 5.0468. Min Act: -0.1700

Data Index: 1299222 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 5.4218. Min Range: -5.4218

Max Act: 5.0468. Min Act: -0.1700

Data Index: 633950 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 5.4218. Min Range: -5.4218

Max Act: 5.0468. Min Act: -0.1699

Data Index: 947838 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 5.4218. Min Range: -5.4218

Max Act: 5.0155. Min Act: -0.1700

Data Index: 358670 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 5.4218. Min Range: -5.4218

Max Act: 4.9843. Min Act: -0.1700

Data Index: 905905 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 5.4218. Min Range: -5.4218

Max Act: 4.9843. Min Act: -0.1700

Data Index: 92603 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 5.4218. Min Range: -5.4218

Max Act: 4.9843. Min Act: -0.1700

Data Index: 640011 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 5.4218. Min Range: -5.4218

Max Act: 4.9843. Min Act: -0.1700

Data Index: 376309 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 5.4218. Min Range: -5.4218

Max Act: 4.8905. Min Act: -0.1700

Data Index: 974904 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 5.4218. Min Range: -5.4218

Max Act: 4.9530. Min Act: -0.1700

Data Index: 903433 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 5.4218. Min Range: -5.4218

Max Act: 5.0155. Min Act: -0.1700

Data Index: 1112931 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 5.4218. Min Range: -5.4218

Max Act: 4.8593. Min Act: -0.1700

Data Index: 885658 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 5.4218. Min Range: -5.4218

Max Act: 4.9218. Min Act: -0.1700

Data Index: 753798 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 5.4218. Min Range: -5.4218

Max Act: 4.9218. Min Act: -0.1700

Data Index: 786649 (C4 (Web Text))

Max Activating Token Index: 471