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

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

Neuron 527 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: 3.0028. Min Range: -3.0028

Max Act: 3.0028. Min Act: -0.1700

Data Index: 872961 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.8760. Min Act: -0.1700

Data Index: 27370 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.8284. Min Act: -0.1700

Data Index: 34582 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.7806. Min Act: -0.1700

Data Index: 338256 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.7646. Min Act: -0.1700

Data Index: 1104660 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.7487. Min Act: -0.1700

Data Index: 103689 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.7167. Min Act: -0.1700

Data Index: 236529 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.7167. Min Act: -0.1700

Data Index: 1150041 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.7167. Min Act: -0.1700

Data Index: 616772 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.7007. Min Act: -0.1700

Data Index: 1031608 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.7007. Min Act: -0.1700

Data Index: 1344401 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.7007. Min Act: -0.1700

Data Index: 379163 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.6527. Min Act: -0.1700

Data Index: 795470 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.6687. Min Act: -0.1700

Data Index: 1150294 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.6205. Min Act: -0.1700

Data Index: 768720 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.6205. Min Act: -0.1700

Data Index: 385935 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.6045. Min Act: -0.1700

Data Index: 624474 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.5884. Min Act: -0.1700

Data Index: 806098 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.6045. Min Act: -0.1700

Data Index: 1318795 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.5884. Min Act: -0.1700

Data Index: 21791 (C4 (Web Text))

Max Activating Token Index: 117