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

Dataset: Open Web Text

Neuron 1641 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: 5.6067. Min Range: -5.6067

Max Act: 5.6067. Min Act: -0.1700

Data Index: 3063647 (Open Web Text)

Max Activating Token Index: 86

Text #1

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.6024. Min Act: -0.1700

Data Index: 3934118 (Open Web Text)

Max Activating Token Index: 436

Text #2

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5939. Min Act: -0.1700

Data Index: 3498883 (Open Web Text)

Max Activating Token Index: 60

Text #3

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5655. Min Act: -0.1700

Data Index: 6021194 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5465. Min Act: -0.1700

Data Index: 6037151 (Open Web Text)

Max Activating Token Index: 662

Text #5

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5565. Min Act: -0.1700

Data Index: 148172 (Open Web Text)

Max Activating Token Index: 462

Text #6

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5255. Min Act: -0.1700

Data Index: 157441 (Open Web Text)

Max Activating Token Index: 144

Text #7

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5220. Min Act: -0.1700

Data Index: 5326251 (Open Web Text)

Max Activating Token Index: 457

Text #8

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5303. Min Act: -0.1700

Data Index: 2733140 (Open Web Text)

Max Activating Token Index: 449

Text #9

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5269. Min Act: -0.1700

Data Index: 910456 (Open Web Text)

Max Activating Token Index: 463

Text #10

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5292. Min Act: -0.1700

Data Index: 847441 (Open Web Text)

Max Activating Token Index: 515

Text #11

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5435. Min Act: -0.1700

Data Index: 7724685 (Open Web Text)

Max Activating Token Index: 557

Text #12

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5349. Min Act: -0.1700

Data Index: 1896032 (Open Web Text)

Max Activating Token Index: 592

Text #13

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5205. Min Act: -0.1700

Data Index: 166702 (Open Web Text)

Max Activating Token Index: 389

Text #14

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5207. Min Act: -0.1700

Data Index: 5900955 (Open Web Text)

Max Activating Token Index: 516

Text #15

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5134. Min Act: -0.1700

Data Index: 31774 (Open Web Text)

Max Activating Token Index: 100

Text #16

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.4829. Min Act: -0.1700

Data Index: 186845 (Open Web Text)

Max Activating Token Index: 145

Text #17

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.4970. Min Act: -0.1700

Data Index: 3731645 (Open Web Text)

Max Activating Token Index: 123

Text #18

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.5030. Min Act: -0.1700

Data Index: 3806760 (Open Web Text)

Max Activating Token Index: 446

Text #19

Max Range: 5.6067. Min Range: -5.6067

Max Act: 5.4834. Min Act: -0.1700

Data Index: 3005466 (Open Web Text)

Max Activating Token Index: 230