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

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

Neuron 1344 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: 3.2891. Min Range: -3.2891

Max Act: 3.2891. Min Act: -0.1700

Data Index: 215745 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.2263. Min Act: -0.1700

Data Index: 135736 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.2105. Min Act: -0.1700

Data Index: 39116 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.2105. Min Act: -0.1700

Data Index: 1177781 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.1948. Min Act: -0.1700

Data Index: 447318 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.1633. Min Act: -0.1700

Data Index: 951792 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.1476. Min Act: -0.1700

Data Index: 322331 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.1318. Min Act: -0.1700

Data Index: 703099 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.1161. Min Act: -0.1700

Data Index: 592626 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.1161. Min Act: -0.1700

Data Index: 968768 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.1003. Min Act: -0.1700

Data Index: 2883 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.1003. Min Act: -0.1700

Data Index: 1228554 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.0845. Min Act: -0.1700

Data Index: 934921 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.0845. Min Act: -0.1700

Data Index: 1115630 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.1003. Min Act: -0.1700

Data Index: 852825 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.0530. Min Act: -0.1700

Data Index: 317297 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.0687. Min Act: -0.1700

Data Index: 314317 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.0687. Min Act: -0.1700

Data Index: 211686 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.0687. Min Act: -0.1700

Data Index: 80765 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 3.2891. Min Range: -3.2891

Max Act: 3.0687. Min Act: -0.1700

Data Index: 1158417 (C4 (Web Text))

Max Activating Token Index: 529