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

Dataset: Open Web Text

Neuron 609 in Layer 5

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: 3.3223. Min Range: -3.3223

Max Act: 3.3161. Min Act: -0.1700

Data Index: 4338038 (Open Web Text)

Max Activating Token Index: 657

Text #1

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.3223. Min Act: -0.1700

Data Index: 7867434 (Open Web Text)

Max Activating Token Index: 598

Text #2

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.2834. Min Act: -0.1700

Data Index: 5729037 (Open Web Text)

Max Activating Token Index: 974

Text #3

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.2633. Min Act: -0.1700

Data Index: 849735 (Open Web Text)

Max Activating Token Index: 615

Text #4

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.2153. Min Act: -0.1700

Data Index: 395502 (Open Web Text)

Max Activating Token Index: 293

Text #5

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.1791. Min Act: -0.1700

Data Index: 8598922 (Open Web Text)

Max Activating Token Index: 930

Text #6

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.2154. Min Act: -0.1700

Data Index: 1641886 (Open Web Text)

Max Activating Token Index: 459

Text #7

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.2001. Min Act: -0.1700

Data Index: 1837908 (Open Web Text)

Max Activating Token Index: 628

Text #8

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.1631. Min Act: -0.1700

Data Index: 839288 (Open Web Text)

Max Activating Token Index: 498

Text #9

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.1629. Min Act: -0.1700

Data Index: 2391235 (Open Web Text)

Max Activating Token Index: 676

Text #10

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.1493. Min Act: -0.1700

Data Index: 3419497 (Open Web Text)

Max Activating Token Index: 883

Text #11

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.1272. Min Act: -0.1700

Data Index: 4654645 (Open Web Text)

Max Activating Token Index: 705

Text #12

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.1258. Min Act: -0.1700

Data Index: 4495447 (Open Web Text)

Max Activating Token Index: 661

Text #13

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.1125. Min Act: -0.1700

Data Index: 2184263 (Open Web Text)

Max Activating Token Index: 832

Text #14

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.1230. Min Act: -0.1700

Data Index: 2287604 (Open Web Text)

Max Activating Token Index: 672

Text #15

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.0767. Min Act: -0.1700

Data Index: 5943389 (Open Web Text)

Max Activating Token Index: 649

Text #16

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.1072. Min Act: -0.1700

Data Index: 8372393 (Open Web Text)

Max Activating Token Index: 611

Text #17

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.1252. Min Act: -0.1700

Data Index: 1365303 (Open Web Text)

Max Activating Token Index: 743

Text #18

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.0610. Min Act: -0.1700

Data Index: 529812 (Open Web Text)

Max Activating Token Index: 583

Text #19

Max Range: 3.3223. Min Range: -3.3223

Max Act: 3.0930. Min Act: -0.1700

Data Index: 3417677 (Open Web Text)

Max Activating Token Index: 905