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

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

Neuron 1548 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.2646. Min Range: -5.2646

Max Act: 5.2646. Min Act: -0.1700

Data Index: 635888 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 5.2646. Min Range: -5.2646

Max Act: 5.1396. Min Act: -0.1700

Data Index: 449828 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 5.2646. Min Range: -5.2646

Max Act: 5.1708. Min Act: -0.1700

Data Index: 738472 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 5.2646. Min Range: -5.2646

Max Act: 5.1083. Min Act: -0.1700

Data Index: 1252708 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 5.2646. Min Range: -5.2646

Max Act: 5.0771. Min Act: -0.1700

Data Index: 197335 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 5.2646. Min Range: -5.2646

Max Act: 5.0458. Min Act: -0.1700

Data Index: 1344873 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 5.2646. Min Range: -5.2646

Max Act: 5.0771. Min Act: -0.1700

Data Index: 1129519 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 5.2646. Min Range: -5.2646

Max Act: 5.0458. Min Act: -0.1700

Data Index: 95746 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 5.2646. Min Range: -5.2646

Max Act: 4.9208. Min Act: -0.1700

Data Index: 56109 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 5.2646. Min Range: -5.2646

Max Act: 4.9833. Min Act: -0.1700

Data Index: 965430 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 5.2646. Min Range: -5.2646

Max Act: 4.9833. Min Act: -0.1700

Data Index: 435822 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 5.2646. Min Range: -5.2646

Max Act: 5.0146. Min Act: -0.1700

Data Index: 1124021 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 5.2646. Min Range: -5.2646

Max Act: 4.9833. Min Act: -0.1700

Data Index: 609057 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 5.2646. Min Range: -5.2646

Max Act: 4.9208. Min Act: -0.1700

Data Index: 264060 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 5.2646. Min Range: -5.2646

Max Act: 4.9208. Min Act: -0.1700

Data Index: 626294 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 5.2646. Min Range: -5.2646

Max Act: 4.9208. Min Act: -0.1700

Data Index: 1072844 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 5.2646. Min Range: -5.2646

Max Act: 4.8583. Min Act: -0.1699

Data Index: 1310320 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 5.2646. Min Range: -5.2646

Max Act: 4.7958. Min Act: -0.1700

Data Index: 1472578 (Python Code)

Max Activating Token Index: 925

Text #18

Max Range: 5.2646. Min Range: -5.2646

Max Act: 4.8271. Min Act: -0.1700

Data Index: 1481128 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 5.2646. Min Range: -5.2646

Max Act: 4.8583. Min Act: -0.1700

Data Index: 799244 (C4 (Web Text))

Max Activating Token Index: 457