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

Dataset: Open Web Text

Neuron 272 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: 3.2440. Min Range: -3.2440

Max Act: 3.2440. Min Act: -0.1700

Data Index: 218154 (Open Web Text)

Max Activating Token Index: 965

Text #1

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.2042. Min Act: -0.1700

Data Index: 2331166 (Open Web Text)

Max Activating Token Index: 194

Text #2

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1869. Min Act: -0.1700

Data Index: 64402 (Open Web Text)

Max Activating Token Index: 798

Text #3

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1993. Min Act: -0.1700

Data Index: 4156493 (Open Web Text)

Max Activating Token Index: 214

Text #4

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1742. Min Act: -0.1700

Data Index: 1783211 (Open Web Text)

Max Activating Token Index: 805

Text #5

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1867. Min Act: -0.1700

Data Index: 144632 (Open Web Text)

Max Activating Token Index: 655

Text #6

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1793. Min Act: -0.1700

Data Index: 1875184 (Open Web Text)

Max Activating Token Index: 911

Text #7

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1445. Min Act: -0.1700

Data Index: 6362059 (Open Web Text)

Max Activating Token Index: 368

Text #8

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1831. Min Act: -0.1700

Data Index: 2105867 (Open Web Text)

Max Activating Token Index: 891

Text #9

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1536. Min Act: -0.1700

Data Index: 3337054 (Open Web Text)

Max Activating Token Index: 834

Text #10

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1459. Min Act: -0.1700

Data Index: 7216678 (Open Web Text)

Max Activating Token Index: 794

Text #11

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1280. Min Act: -0.1700

Data Index: 2485371 (Open Web Text)

Max Activating Token Index: 672

Text #12

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1180. Min Act: -0.1700

Data Index: 8585746 (Open Web Text)

Max Activating Token Index: 193

Text #13

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1176. Min Act: -0.1700

Data Index: 7028960 (Open Web Text)

Max Activating Token Index: 308

Text #14

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1205. Min Act: -0.1700

Data Index: 1112444 (Open Web Text)

Max Activating Token Index: 275

Text #15

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1275. Min Act: -0.1700

Data Index: 6321192 (Open Web Text)

Max Activating Token Index: 298

Text #16

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1327. Min Act: -0.1700

Data Index: 3707776 (Open Web Text)

Max Activating Token Index: 849

Text #17

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.1019. Min Act: -0.1700

Data Index: 613931 (Open Web Text)

Max Activating Token Index: 379

Text #18

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.0770. Min Act: -0.1700

Data Index: 6173151 (Open Web Text)

Max Activating Token Index: 798

Text #19

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.0846. Min Act: -0.1700

Data Index: 1738060 (Open Web Text)

Max Activating Token Index: 545