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

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

Neuron 720 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.8776. Min Act: -0.1700

Data Index: 90820 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.8463. Min Act: -0.1700

Data Index: 1004363 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.7837. Min Act: -0.1700

Data Index: 993731 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.8150. Min Act: -0.1700

Data Index: 673000 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.8150. Min Act: -0.1700

Data Index: 331042 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.8150. Min Act: -0.1700

Data Index: 154839 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.7837. Min Act: -0.1700

Data Index: 194221 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.7837. Min Act: -0.1700

Data Index: 24334 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.8150. Min Act: -0.1700

Data Index: 1242447 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.8150. Min Act: -0.1700

Data Index: 943850 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.7524. Min Act: -0.1700

Data Index: 871107 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.7837. Min Act: -0.1700

Data Index: 949972 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.7837. Min Act: -0.1700

Data Index: 957241 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.8150. Min Act: -0.1700

Data Index: 970409 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.7524. Min Act: -0.1700

Data Index: 564587 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.7524. Min Act: -0.1700

Data Index: 138291 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.8150. Min Act: -0.1700

Data Index: 1153306 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.7837. Min Act: -0.1700

Data Index: 1172885 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.7837. Min Act: -0.1700

Data Index: 616289 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 3.8776. Min Range: -3.8776

Max Act: 3.7524. Min Act: -0.1700

Data Index: 333317 (C4 (Web Text))

Max Activating Token Index: 34