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

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

Neuron 195 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: 5.6237. Min Range: -5.6237

Max Act: 5.6237. Min Act: -0.1700

Data Index: 133057 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.4987. Min Act: -0.1700

Data Index: 1055009 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.4050. Min Act: -0.1700

Data Index: 1147064 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.3737. Min Act: -0.1700

Data Index: 763077 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.2487. Min Act: -0.1700

Data Index: 230796 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.2800. Min Act: -0.1700

Data Index: 293817 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.2487. Min Act: -0.1700

Data Index: 438149 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.2487. Min Act: -0.1700

Data Index: 764407 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.2175. Min Act: -0.1700

Data Index: 1027137 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.1862. Min Act: -0.1700

Data Index: 1043881 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.1862. Min Act: -0.1700

Data Index: 277842 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.1237. Min Act: -0.1700

Data Index: 1218794 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.1550. Min Act: -0.1700

Data Index: 85088 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.2175. Min Act: -0.1700

Data Index: 608107 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.1237. Min Act: -0.1700

Data Index: 9685 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.1862. Min Act: -0.1700

Data Index: 1349624 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.0925. Min Act: -0.1700

Data Index: 1142731 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.1862. Min Act: -0.1700

Data Index: 1003626 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.1862. Min Act: -0.1700

Data Index: 70956 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 5.6237. Min Range: -5.6237

Max Act: 5.1237. Min Act: -0.1700

Data Index: 933202 (C4 (Web Text))

Max Activating Token Index: 956