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

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

Neuron 1142 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.4783. Min Act: -0.1700

Data Index: 1248573 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.3685. Min Act: -0.1700

Data Index: 1118193 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.3685. Min Act: -0.1700

Data Index: 785478 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.2743. Min Act: -0.1700

Data Index: 158296 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.3214. Min Act: -0.1700

Data Index: 10566 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.3528. Min Act: -0.1700

Data Index: 1060981 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.3214. Min Act: -0.1700

Data Index: 255619 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.2586. Min Act: -0.1700

Data Index: 968766 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.3371. Min Act: -0.1700

Data Index: 1138904 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.2743. Min Act: -0.1700

Data Index: 974996 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.3057. Min Act: -0.1700

Data Index: 1192763 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.3057. Min Act: -0.1700

Data Index: 1237874 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.2900. Min Act: -0.1700

Data Index: 51173 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.3057. Min Act: -0.1700

Data Index: 568317 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.2900. Min Act: -0.1700

Data Index: 799128 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.2743. Min Act: -0.1700

Data Index: 1155775 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.2586. Min Act: -0.1700

Data Index: 240598 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.2900. Min Act: -0.1700

Data Index: 413117 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.2114. Min Act: -0.1700

Data Index: 211113 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 3.4783. Min Range: -3.4783

Max Act: 3.2586. Min Act: -0.1700

Data Index: 347551 (C4 (Web Text))

Max Activating Token Index: 670