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

Dataset: Open Web Text

Neuron 1259 in Layer 4

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: 3.9655. Min Range: -3.9655

Max Act: 3.9655. Min Act: -0.1700

Data Index: 5244678 (Open Web Text)

Max Activating Token Index: 777

Text #1

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.9126. Min Act: -0.1700

Data Index: 353527 (Open Web Text)

Max Activating Token Index: 68

Text #2

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.9243. Min Act: -0.1700

Data Index: 8355181 (Open Web Text)

Max Activating Token Index: 943

Text #3

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.8888. Min Act: -0.1700

Data Index: 2602294 (Open Web Text)

Max Activating Token Index: 487

Text #4

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.8424. Min Act: -0.1700

Data Index: 5132007 (Open Web Text)

Max Activating Token Index: 941

Text #5

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.8343. Min Act: -0.1700

Data Index: 4698494 (Open Web Text)

Max Activating Token Index: 274

Text #6

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.7835. Min Act: -0.1700

Data Index: 8643582 (Open Web Text)

Max Activating Token Index: 402

Text #7

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.8273. Min Act: -0.1700

Data Index: 3522668 (Open Web Text)

Max Activating Token Index: 696

Text #8

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.8322. Min Act: -0.1700

Data Index: 146951 (Open Web Text)

Max Activating Token Index: 633

Text #9

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.8213. Min Act: -0.1700

Data Index: 643990 (Open Web Text)

Max Activating Token Index: 1012

Text #10

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.7995. Min Act: -0.1700

Data Index: 1921133 (Open Web Text)

Max Activating Token Index: 825

Text #11

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.7826. Min Act: -0.1700

Data Index: 7795458 (Open Web Text)

Max Activating Token Index: 827

Text #12

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.8030. Min Act: -0.1700

Data Index: 7554744 (Open Web Text)

Max Activating Token Index: 389

Text #13

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.7246. Min Act: -0.1700

Data Index: 7638492 (Open Web Text)

Max Activating Token Index: 232

Text #14

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.6971. Min Act: -0.1700

Data Index: 8451356 (Open Web Text)

Max Activating Token Index: 872

Text #15

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.7382. Min Act: -0.1700

Data Index: 6109179 (Open Web Text)

Max Activating Token Index: 497

Text #16

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.7022. Min Act: -0.1700

Data Index: 2432611 (Open Web Text)

Max Activating Token Index: 361

Text #17

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.6636. Min Act: -0.1700

Data Index: 4654338 (Open Web Text)

Max Activating Token Index: 183

Text #18

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.6942. Min Act: -0.1700

Data Index: 6988767 (Open Web Text)

Max Activating Token Index: 921

Text #19

Max Range: 3.9655. Min Range: -3.9655

Max Act: 3.6672. Min Act: -0.1700

Data Index: 2697582 (Open Web Text)

Max Activating Token Index: 795