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

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

Neuron 1952 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: 3.2762. Min Range: -3.2762

Max Act: 3.2762. Min Act: -0.1700

Data Index: 1181895 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2762. Min Act: -0.1700

Data Index: 988392 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2762. Min Act: -0.1700

Data Index: 765961 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2605. Min Act: -0.1700

Data Index: 360736 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2605. Min Act: -0.1700

Data Index: 741435 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2448. Min Act: -0.1700

Data Index: 36343 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2290. Min Act: -0.1700

Data Index: 401457 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2448. Min Act: -0.1700

Data Index: 1027388 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2448. Min Act: -0.1700

Data Index: 779849 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2448. Min Act: -0.1700

Data Index: 1106839 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2448. Min Act: -0.1700

Data Index: 1318492 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2290. Min Act: -0.1700

Data Index: 999343 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2133. Min Act: -0.1700

Data Index: 845446 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2290. Min Act: -0.1700

Data Index: 661921 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2290. Min Act: -0.1700

Data Index: 921267 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2290. Min Act: -0.1700

Data Index: 674263 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2133. Min Act: -0.1700

Data Index: 694830 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2448. Min Act: -0.1700

Data Index: 700720 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2290. Min Act: -0.1700

Data Index: 1147449 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2133. Min Act: -0.1700

Data Index: 384975 (C4 (Web Text))

Max Activating Token Index: 33