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

Dataset: Open Web Text

Neuron 2639 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: 3.6835. Min Range: -3.6835

Max Act: 3.6835. Min Act: -0.1700

Data Index: 3909100 (Open Web Text)

Max Activating Token Index: 595

Text #1

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.6268. Min Act: -0.1700

Data Index: 8759245 (Open Web Text)

Max Activating Token Index: 621

Text #2

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.5450. Min Act: -0.1700

Data Index: 4499145 (Open Web Text)

Max Activating Token Index: 674

Text #3

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.5554. Min Act: -0.1700

Data Index: 1426862 (Open Web Text)

Max Activating Token Index: 198

Text #4

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.5184. Min Act: -0.1700

Data Index: 4285621 (Open Web Text)

Max Activating Token Index: 311

Text #5

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.5115. Min Act: -0.1700

Data Index: 4507175 (Open Web Text)

Max Activating Token Index: 441

Text #6

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.5132. Min Act: -0.1700

Data Index: 8463841 (Open Web Text)

Max Activating Token Index: 757

Text #7

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.4754. Min Act: -0.1700

Data Index: 1590083 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.4436. Min Act: -0.1700

Data Index: 5307759 (Open Web Text)

Max Activating Token Index: 703

Text #9

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.4662. Min Act: -0.1700

Data Index: 5736723 (Open Web Text)

Max Activating Token Index: 1002

Text #10

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.4520. Min Act: -0.1700

Data Index: 1539371 (Open Web Text)

Max Activating Token Index: 482

Text #11

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.4369. Min Act: -0.1700

Data Index: 7190361 (Open Web Text)

Max Activating Token Index: 859

Text #12

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.4412. Min Act: -0.1700

Data Index: 1872814 (Open Web Text)

Max Activating Token Index: 162

Text #13

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.4246. Min Act: -0.1700

Data Index: 8211117 (Open Web Text)

Max Activating Token Index: 410

Text #14

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.4363. Min Act: -0.1700

Data Index: 6822501 (Open Web Text)

Max Activating Token Index: 544

Text #15

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.3983. Min Act: -0.1700

Data Index: 2639079 (Open Web Text)

Max Activating Token Index: 892

Text #16

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.4426. Min Act: -0.1700

Data Index: 2667624 (Open Web Text)

Max Activating Token Index: 689

Text #17

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.4364. Min Act: -0.1700

Data Index: 3737245 (Open Web Text)

Max Activating Token Index: 452

Text #18

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.4372. Min Act: -0.1700

Data Index: 6592581 (Open Web Text)

Max Activating Token Index: 842

Text #19

Max Range: 3.6835. Min Range: -3.6835

Max Act: 3.4193. Min Act: -0.1700

Data Index: 5213986 (Open Web Text)

Max Activating Token Index: 267