Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2104 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.6784. Min Act: -0.1700

Data Index: 2536220 (Open Web Text)

Max Activating Token Index: 219

Text #1

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.6518. Min Act: -0.1700

Data Index: 6738692 (Open Web Text)

Max Activating Token Index: 469

Text #2

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.6355. Min Act: -0.1700

Data Index: 8362511 (Open Web Text)

Max Activating Token Index: 801

Text #3

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.6391. Min Act: -0.1700

Data Index: 4518364 (Open Web Text)

Max Activating Token Index: 232

Text #4

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.6163. Min Act: -0.1700

Data Index: 6655030 (Open Web Text)

Max Activating Token Index: 417

Text #5

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.6051. Min Act: -0.1700

Data Index: 6888594 (Open Web Text)

Max Activating Token Index: 620

Text #6

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.6087. Min Act: -0.1700

Data Index: 756679 (Open Web Text)

Max Activating Token Index: 715

Text #7

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5824. Min Act: -0.1700

Data Index: 8823975 (Open Web Text)

Max Activating Token Index: 978

Text #8

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5705. Min Act: -0.1700

Data Index: 1119699 (Open Web Text)

Max Activating Token Index: 863

Text #9

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5563. Min Act: -0.1700

Data Index: 2801351 (Open Web Text)

Max Activating Token Index: 265

Text #10

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5786. Min Act: -0.1700

Data Index: 2650270 (Open Web Text)

Max Activating Token Index: 745

Text #11

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5640. Min Act: -0.1700

Data Index: 3711829 (Open Web Text)

Max Activating Token Index: 666

Text #12

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5722. Min Act: -0.1700

Data Index: 8470345 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5432. Min Act: -0.1700

Data Index: 5827839 (Open Web Text)

Max Activating Token Index: 102

Text #14

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5523. Min Act: -0.1700

Data Index: 719595 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5483. Min Act: -0.1700

Data Index: 3176706 (Open Web Text)

Max Activating Token Index: 387

Text #16

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5200. Min Act: -0.1700

Data Index: 1617460 (Open Web Text)

Max Activating Token Index: 305

Text #17

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.4907. Min Act: -0.1700

Data Index: 4740426 (Open Web Text)

Max Activating Token Index: 902

Text #18

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5023. Min Act: -0.1700

Data Index: 6214524 (Open Web Text)

Max Activating Token Index: 902

Text #19

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.4946. Min Act: -0.1700

Data Index: 2745947 (Open Web Text)

Max Activating Token Index: 965