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

Dataset: Open Web Text

Neuron 240 in Layer 0

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: 1.6651. Min Range: -1.6651

Max Act: 1.6618. Min Act: -0.1700

Data Index: 2724333 (Open Web Text)

Max Activating Token Index: 343

Text #1

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6590. Min Act: -0.1697

Data Index: 4863072 (Open Web Text)

Max Activating Token Index: 496

Text #2

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6651. Min Act: -0.1642

Data Index: 714403 (Open Web Text)

Max Activating Token Index: 198

Text #3

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6553. Min Act: -0.1698

Data Index: 2267906 (Open Web Text)

Max Activating Token Index: 238

Text #4

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6505. Min Act: -0.1700

Data Index: 6682846 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6404. Min Act: -0.1699

Data Index: 1896822 (Open Web Text)

Max Activating Token Index: 238

Text #6

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6395. Min Act: -0.1699

Data Index: 1303544 (Open Web Text)

Max Activating Token Index: 134

Text #7

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6380. Min Act: -0.1628

Data Index: 3980442 (Open Web Text)

Max Activating Token Index: 50

Text #8

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6300. Min Act: -0.1699

Data Index: 5676847 (Open Web Text)

Max Activating Token Index: 742

Text #9

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6386. Min Act: -0.1690

Data Index: 1081322 (Open Web Text)

Max Activating Token Index: 27

Text #10

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6227. Min Act: -0.1700

Data Index: 7914107 (Open Web Text)

Max Activating Token Index: 520

Text #11

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6230. Min Act: -0.1671

Data Index: 3199226 (Open Web Text)

Max Activating Token Index: 243

Text #12

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6107. Min Act: -0.1700

Data Index: 8314010 (Open Web Text)

Max Activating Token Index: 292

Text #13

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6116. Min Act: -0.1700

Data Index: 5372415 (Open Web Text)

Max Activating Token Index: 65

Text #14

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6226. Min Act: -0.1700

Data Index: 7316411 (Open Web Text)

Max Activating Token Index: 271

Text #15

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6013. Min Act: -0.1690

Data Index: 2450922 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6073. Min Act: -0.1699

Data Index: 5918577 (Open Web Text)

Max Activating Token Index: 19

Text #17

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.6098. Min Act: -0.1700

Data Index: 3324812 (Open Web Text)

Max Activating Token Index: 177

Text #18

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.5967. Min Act: -0.1700

Data Index: 2602479 (Open Web Text)

Max Activating Token Index: 448

Text #19

Max Range: 1.6651. Min Range: -1.6651

Max Act: 1.5973. Min Act: -0.1700

Data Index: 8267717 (Open Web Text)

Max Activating Token Index: 144