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

Dataset: Open Web Text

Neuron 891 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: 4.8284. Min Range: -4.8284

Max Act: 4.8284. Min Act: -0.1700

Data Index: 956520 (Open Web Text)

Max Activating Token Index: 927

Text #1

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.7374. Min Act: -0.1700

Data Index: 6651787 (Open Web Text)

Max Activating Token Index: 430

Text #2

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.7745. Min Act: -0.1700

Data Index: 8036037 (Open Web Text)

Max Activating Token Index: 637

Text #3

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.7303. Min Act: -0.1700

Data Index: 1250821 (Open Web Text)

Max Activating Token Index: 582

Text #4

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.7276. Min Act: -0.1700

Data Index: 2324351 (Open Web Text)

Max Activating Token Index: 840

Text #5

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.7482. Min Act: -0.1700

Data Index: 6452003 (Open Web Text)

Max Activating Token Index: 140

Text #6

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.7500. Min Act: -0.1700

Data Index: 5963439 (Open Web Text)

Max Activating Token Index: 746

Text #7

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.6767. Min Act: -0.1700

Data Index: 7405521 (Open Web Text)

Max Activating Token Index: 1014

Text #8

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.6728. Min Act: -0.1700

Data Index: 3296455 (Open Web Text)

Max Activating Token Index: 227

Text #9

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.6819. Min Act: -0.1700

Data Index: 3752437 (Open Web Text)

Max Activating Token Index: 386

Text #10

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.6842. Min Act: -0.1700

Data Index: 3020110 (Open Web Text)

Max Activating Token Index: 118

Text #11

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.6356. Min Act: -0.1700

Data Index: 7197823 (Open Web Text)

Max Activating Token Index: 367

Text #12

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.6720. Min Act: -0.1700

Data Index: 8691287 (Open Web Text)

Max Activating Token Index: 412

Text #13

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.6853. Min Act: -0.1700

Data Index: 8375220 (Open Web Text)

Max Activating Token Index: 734

Text #14

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.6862. Min Act: -0.1700

Data Index: 1509562 (Open Web Text)

Max Activating Token Index: 876

Text #15

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.6429. Min Act: -0.1700

Data Index: 6061803 (Open Web Text)

Max Activating Token Index: 269

Text #16

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.6654. Min Act: -0.1700

Data Index: 5344433 (Open Web Text)

Max Activating Token Index: 843

Text #17

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.6419. Min Act: -0.1700

Data Index: 5128453 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.6180. Min Act: -0.1700

Data Index: 2494757 (Open Web Text)

Max Activating Token Index: 668

Text #19

Max Range: 4.8284. Min Range: -4.8284

Max Act: 4.6382. Min Act: -0.1700

Data Index: 4592370 (Open Web Text)

Max Activating Token Index: 96