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

Dataset: Open Web Text

Neuron 2850 in Layer 1

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: 4.8355. Min Range: -4.8355

Max Act: 4.8355. Min Act: -0.1700

Data Index: 919510 (Open Web Text)

Max Activating Token Index: 233

Text #1

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.8209. Min Act: -0.1700

Data Index: 5945039 (Open Web Text)

Max Activating Token Index: 142

Text #2

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.8299. Min Act: -0.1700

Data Index: 4761270 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.8273. Min Act: -0.1700

Data Index: 8518434 (Open Web Text)

Max Activating Token Index: 218

Text #4

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.8246. Min Act: -0.1700

Data Index: 5067035 (Open Web Text)

Max Activating Token Index: 492

Text #5

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.8019. Min Act: -0.1700

Data Index: 5232997 (Open Web Text)

Max Activating Token Index: 314

Text #6

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.7945. Min Act: -0.1700

Data Index: 562378 (Open Web Text)

Max Activating Token Index: 182

Text #7

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.8022. Min Act: -0.1700

Data Index: 6136332 (Open Web Text)

Max Activating Token Index: 122

Text #8

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.8064. Min Act: -0.1700

Data Index: 5160681 (Open Web Text)

Max Activating Token Index: 538

Text #9

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.8004. Min Act: -0.1700

Data Index: 8712994 (Open Web Text)

Max Activating Token Index: 214

Text #10

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.7892. Min Act: -0.1700

Data Index: 7756638 (Open Web Text)

Max Activating Token Index: 455

Text #11

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.8187. Min Act: -0.1700

Data Index: 6272533 (Open Web Text)

Max Activating Token Index: 399

Text #12

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.7738. Min Act: -0.1700

Data Index: 539260 (Open Web Text)

Max Activating Token Index: 558

Text #13

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.7671. Min Act: -0.1700

Data Index: 1557252 (Open Web Text)

Max Activating Token Index: 242

Text #14

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.7740. Min Act: -0.1700

Data Index: 1689903 (Open Web Text)

Max Activating Token Index: 272

Text #15

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.7679. Min Act: -0.1700

Data Index: 1867210 (Open Web Text)

Max Activating Token Index: 177

Text #16

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.7691. Min Act: -0.1700

Data Index: 5291319 (Open Web Text)

Max Activating Token Index: 630

Text #17

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.7876. Min Act: -0.1700

Data Index: 5813487 (Open Web Text)

Max Activating Token Index: 594

Text #18

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.7489. Min Act: -0.1700

Data Index: 637367 (Open Web Text)

Max Activating Token Index: 729

Text #19

Max Range: 4.8355. Min Range: -4.8355

Max Act: 4.7826. Min Act: -0.1700

Data Index: 5957758 (Open Web Text)

Max Activating Token Index: 292