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

Dataset: Open Web Text

Neuron 728 in Layer 3

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: 4.0850. Min Range: -4.0850

Max Act: 4.0260. Min Act: -0.1700

Data Index: 6995134 (Open Web Text)

Max Activating Token Index: 470

Text #1

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9620. Min Act: -0.1700

Data Index: 3506996 (Open Web Text)

Max Activating Token Index: 462

Text #2

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9876. Min Act: -0.1700

Data Index: 2222343 (Open Web Text)

Max Activating Token Index: 684

Text #3

Max Range: 4.0850. Min Range: -4.0850

Max Act: 4.0345. Min Act: -0.1700

Data Index: 3039532 (Open Web Text)

Max Activating Token Index: 814

Text #4

Max Range: 4.0850. Min Range: -4.0850

Max Act: 4.0412. Min Act: -0.1700

Data Index: 421796 (Open Web Text)

Max Activating Token Index: 809

Text #5

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9638. Min Act: -0.1700

Data Index: 7581122 (Open Web Text)

Max Activating Token Index: 593

Text #6

Max Range: 4.0850. Min Range: -4.0850

Max Act: 4.0427. Min Act: -0.1700

Data Index: 2457183 (Open Web Text)

Max Activating Token Index: 830

Text #7

Max Range: 4.0850. Min Range: -4.0850

Max Act: 4.0382. Min Act: -0.1700

Data Index: 3218588 (Open Web Text)

Max Activating Token Index: 58

Text #8

Max Range: 4.0850. Min Range: -4.0850

Max Act: 4.0318. Min Act: -0.1700

Data Index: 6113032 (Open Web Text)

Max Activating Token Index: 336

Text #9

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9435. Min Act: -0.1700

Data Index: 8266924 (Open Web Text)

Max Activating Token Index: 625

Text #10

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9613. Min Act: -0.1700

Data Index: 8028773 (Open Web Text)

Max Activating Token Index: 738

Text #11

Max Range: 4.0850. Min Range: -4.0850

Max Act: 4.0850. Min Act: -0.1700

Data Index: 7932873 (Open Web Text)

Max Activating Token Index: 915

Text #12

Max Range: 4.0850. Min Range: -4.0850

Max Act: 4.0043. Min Act: -0.1700

Data Index: 6757874 (Open Web Text)

Max Activating Token Index: 570

Text #13

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.8466. Min Act: -0.1700

Data Index: 8330647 (Open Web Text)

Max Activating Token Index: 329

Text #14

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.8093. Min Act: -0.1700

Data Index: 1869656 (Open Web Text)

Max Activating Token Index: 472

Text #15

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9835. Min Act: -0.1700

Data Index: 838141 (Open Web Text)

Max Activating Token Index: 243

Text #16

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9279. Min Act: -0.1700

Data Index: 5290284 (Open Web Text)

Max Activating Token Index: 920

Text #17

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9773. Min Act: -0.1700

Data Index: 788308 (Open Web Text)

Max Activating Token Index: 278

Text #18

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.8103. Min Act: -0.1700

Data Index: 4017543 (Open Web Text)

Max Activating Token Index: 514

Text #19

Max Range: 4.0850. Min Range: -4.0850

Max Act: 3.9686. Min Act: -0.1700

Data Index: 7795935 (Open Web Text)

Max Activating Token Index: 256