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

Dataset: Open Web Text

Neuron 479 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: 1.8530. Min Range: -1.8530

Max Act: 1.7814. Min Act: -0.1700

Data Index: 4824096 (Open Web Text)

Max Activating Token Index: 765

Text #1

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8085. Min Act: -0.1700

Data Index: 4052301 (Open Web Text)

Max Activating Token Index: 599

Text #2

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8375. Min Act: -0.1700

Data Index: 3930583 (Open Web Text)

Max Activating Token Index: 487

Text #3

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8486. Min Act: -0.1700

Data Index: 5311413 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8104. Min Act: -0.1700

Data Index: 4734299 (Open Web Text)

Max Activating Token Index: 393

Text #5

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8135. Min Act: -0.1700

Data Index: 3005834 (Open Web Text)

Max Activating Token Index: 608

Text #6

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8530. Min Act: -0.1700

Data Index: 5411689 (Open Web Text)

Max Activating Token Index: 243

Text #7

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8275. Min Act: -0.1700

Data Index: 4773381 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8236. Min Act: -0.1700

Data Index: 4231406 (Open Web Text)

Max Activating Token Index: 784

Text #9

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8414. Min Act: -0.1700

Data Index: 7713571 (Open Web Text)

Max Activating Token Index: 858

Text #10

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8147. Min Act: -0.1700

Data Index: 3273864 (Open Web Text)

Max Activating Token Index: 1009

Text #11

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8236. Min Act: -0.1700

Data Index: 6641766 (Open Web Text)

Max Activating Token Index: 868

Text #12

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.7898. Min Act: -0.1700

Data Index: 2963976 (Open Web Text)

Max Activating Token Index: 317

Text #13

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8086. Min Act: -0.1700

Data Index: 7702298 (Open Web Text)

Max Activating Token Index: 967

Text #14

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8376. Min Act: -0.1700

Data Index: 296647 (Open Web Text)

Max Activating Token Index: 165

Text #15

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.7646. Min Act: -0.1700

Data Index: 4808539 (Open Web Text)

Max Activating Token Index: 376

Text #16

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8223. Min Act: -0.1700

Data Index: 2528020 (Open Web Text)

Max Activating Token Index: 801

Text #17

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.7531. Min Act: -0.1700

Data Index: 6162792 (Open Web Text)

Max Activating Token Index: 979

Text #18

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8030. Min Act: -0.1700

Data Index: 4487470 (Open Web Text)

Max Activating Token Index: 958

Text #19

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.7929. Min Act: -0.1700

Data Index: 4971982 (Open Web Text)

Max Activating Token Index: 1006