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

Dataset: Open Web Text

Neuron 23 in Layer 2

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: 4.8255. Min Range: -4.8255

Max Act: 4.8255. Min Act: -0.1700

Data Index: 785805 (Open Web Text)

Max Activating Token Index: 511

Text #1

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7894. Min Act: -0.1700

Data Index: 6832784 (Open Web Text)

Max Activating Token Index: 94

Text #2

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7836. Min Act: -0.1700

Data Index: 7620901 (Open Web Text)

Max Activating Token Index: 263

Text #3

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7883. Min Act: -0.1700

Data Index: 7894034 (Open Web Text)

Max Activating Token Index: 532

Text #4

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7691. Min Act: -0.1700

Data Index: 1508396 (Open Web Text)

Max Activating Token Index: 797

Text #5

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7582. Min Act: -0.1700

Data Index: 8190378 (Open Web Text)

Max Activating Token Index: 343

Text #6

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7395. Min Act: -0.1700

Data Index: 6510221 (Open Web Text)

Max Activating Token Index: 477

Text #7

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7317. Min Act: -0.1700

Data Index: 3483902 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7346. Min Act: -0.1700

Data Index: 6803977 (Open Web Text)

Max Activating Token Index: 150

Text #9

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7317. Min Act: -0.1700

Data Index: 6947672 (Open Web Text)

Max Activating Token Index: 401

Text #10

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7391. Min Act: -0.1700

Data Index: 8030215 (Open Web Text)

Max Activating Token Index: 696

Text #11

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7419. Min Act: -0.1700

Data Index: 8026653 (Open Web Text)

Max Activating Token Index: 528

Text #12

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7018. Min Act: -0.1700

Data Index: 2905097 (Open Web Text)

Max Activating Token Index: 637

Text #13

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7211. Min Act: -0.1700

Data Index: 1220967 (Open Web Text)

Max Activating Token Index: 418

Text #14

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7012. Min Act: -0.1700

Data Index: 8314556 (Open Web Text)

Max Activating Token Index: 409

Text #15

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7014. Min Act: -0.1700

Data Index: 7497600 (Open Web Text)

Max Activating Token Index: 447

Text #16

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.6995. Min Act: -0.1700

Data Index: 7100949 (Open Web Text)

Max Activating Token Index: 587

Text #17

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7000. Min Act: -0.1700

Data Index: 4222553 (Open Web Text)

Max Activating Token Index: 399

Text #18

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.7184. Min Act: -0.1700

Data Index: 3301522 (Open Web Text)

Max Activating Token Index: 599

Text #19

Max Range: 4.8255. Min Range: -4.8255

Max Act: 4.6979. Min Act: -0.1700

Data Index: 6594506 (Open Web Text)

Max Activating Token Index: 876