Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 629 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.3891. Min Act: -0.1700

Data Index: 1447619 (Python Code)

Max Activating Token Index: 249

Text #1

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.3734. Min Act: -0.1700

Data Index: 1532626 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.3577. Min Act: -0.1700

Data Index: 1511774 (Python Code)

Max Activating Token Index: 193

Text #3

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.3263. Min Act: -0.1700

Data Index: 1537794 (Python Code)

Max Activating Token Index: 765

Text #4

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.3106. Min Act: -0.1700

Data Index: 1473190 (Python Code)

Max Activating Token Index: 233

Text #5

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.3106. Min Act: -0.1700

Data Index: 276314 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.2792. Min Act: -0.1700

Data Index: 446707 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.3106. Min Act: -0.1700

Data Index: 1515083 (Python Code)

Max Activating Token Index: 631

Text #8

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.2792. Min Act: -0.1700

Data Index: 1302442 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.2792. Min Act: -0.1700

Data Index: 1488235 (Python Code)

Max Activating Token Index: 802

Text #10

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.2635. Min Act: -0.1700

Data Index: 1475376 (Python Code)

Max Activating Token Index: 199

Text #11

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.2635. Min Act: -0.1700

Data Index: 1604826 (Python Code)

Max Activating Token Index: 511

Text #12

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.2635. Min Act: -0.1700

Data Index: 750600 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.2635. Min Act: -0.1700

Data Index: 1125502 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.2792. Min Act: -0.1700

Data Index: 1175649 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.2477. Min Act: -0.1700

Data Index: 682959 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.2320. Min Act: -0.1700

Data Index: 889259 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.2477. Min Act: -0.1700

Data Index: 720780 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.2477. Min Act: -0.1700

Data Index: 1609653 (Python Code)

Max Activating Token Index: 183

Text #19

Max Range: 3.3891. Min Range: -3.3891

Max Act: 3.2006. Min Act: -0.1700

Data Index: 1417736 (Python Code)

Max Activating Token Index: 814