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

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

Neuron 207 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.6827. Min Act: -0.1700

Data Index: 340487 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.6827. Min Act: -0.1700

Data Index: 175811 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.5889. Min Act: -0.1700

Data Index: 228457 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.6202. Min Act: -0.1700

Data Index: 587469 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.6514. Min Act: -0.1700

Data Index: 993084 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.5889. Min Act: -0.1700

Data Index: 30437 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.5889. Min Act: -0.1700

Data Index: 642007 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.5889. Min Act: -0.1700

Data Index: 1263789 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.5264. Min Act: -0.1700

Data Index: 1243479 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.5577. Min Act: -0.1700

Data Index: 480920 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.4952. Min Act: -0.1700

Data Index: 731158 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.4639. Min Act: -0.1700

Data Index: 517231 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.4327. Min Act: -0.1700

Data Index: 1037622 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.4639. Min Act: -0.1700

Data Index: 276163 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.5264. Min Act: -0.1700

Data Index: 276205 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.5264. Min Act: -0.1700

Data Index: 1138307 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.4639. Min Act: -0.1700

Data Index: 947815 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.3702. Min Act: -0.1700

Data Index: 938486 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.4639. Min Act: -0.1700

Data Index: 856708 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 5.6827. Min Range: -5.6827

Max Act: 5.4639. Min Act: -0.1700

Data Index: 420497 (C4 (Web Text))

Max Activating Token Index: 156