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

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

Neuron 1539 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: 3.1868. Min Range: -3.1868

Max Act: 3.1868. Min Act: -0.1700

Data Index: 945291 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.1396. Min Act: -0.1700

Data Index: 826952 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.1396. Min Act: -0.1700

Data Index: 416817 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.1554. Min Act: -0.1700

Data Index: 940503 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.1081. Min Act: -0.1700

Data Index: 463146 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.1081. Min Act: -0.1700

Data Index: 895173 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.1081. Min Act: -0.1700

Data Index: 819653 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.1081. Min Act: -0.1700

Data Index: 503382 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.1081. Min Act: -0.1700

Data Index: 1045138 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.1081. Min Act: -0.1700

Data Index: 982393 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.0923. Min Act: -0.1700

Data Index: 967224 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.1081. Min Act: -0.1700

Data Index: 106147 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.0923. Min Act: -0.1700

Data Index: 1164068 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.0923. Min Act: -0.1700

Data Index: 1269594 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.0923. Min Act: -0.1700

Data Index: 1217574 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.0608. Min Act: -0.1700

Data Index: 362109 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.0766. Min Act: -0.1700

Data Index: 38204 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.0923. Min Act: -0.1700

Data Index: 160790 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.0766. Min Act: -0.1700

Data Index: 589872 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 3.1868. Min Range: -3.1868

Max Act: 3.0923. Min Act: -0.1700

Data Index: 160090 (C4 (Web Text))

Max Activating Token Index: 140