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

Dataset: Open Web Text

Neuron 2243 in Layer 6

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: 3.4306. Min Range: -3.4306

Max Act: 3.4306. Min Act: -0.1700

Data Index: 2067271 (Open Web Text)

Max Activating Token Index: 804

Text #1

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.3639. Min Act: -0.1700

Data Index: 1625834 (Open Web Text)

Max Activating Token Index: 45

Text #2

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.3404. Min Act: -0.1700

Data Index: 7156689 (Open Web Text)

Max Activating Token Index: 254

Text #3

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.2197. Min Act: -0.1700

Data Index: 3591310 (Open Web Text)

Max Activating Token Index: 875

Text #4

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.2328. Min Act: -0.1700

Data Index: 8811843 (Open Web Text)

Max Activating Token Index: 432

Text #5

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.2300. Min Act: -0.1700

Data Index: 6297200 (Open Web Text)

Max Activating Token Index: 209

Text #6

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.2142. Min Act: -0.1700

Data Index: 3844339 (Open Web Text)

Max Activating Token Index: 179

Text #7

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.1801. Min Act: -0.1700

Data Index: 3075967 (Open Web Text)

Max Activating Token Index: 510

Text #8

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.1591. Min Act: -0.1700

Data Index: 2064835 (Open Web Text)

Max Activating Token Index: 517

Text #9

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.2065. Min Act: -0.1700

Data Index: 2320463 (Open Web Text)

Max Activating Token Index: 40

Text #10

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.1308. Min Act: -0.1700

Data Index: 6510634 (Open Web Text)

Max Activating Token Index: 920

Text #11

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.1610. Min Act: -0.1700

Data Index: 8179280 (Open Web Text)

Max Activating Token Index: 535

Text #12

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.1491. Min Act: -0.1700

Data Index: 6300672 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.1284. Min Act: -0.1700

Data Index: 5808474 (Open Web Text)

Max Activating Token Index: 254

Text #14

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.1218. Min Act: -0.1700

Data Index: 3665243 (Open Web Text)

Max Activating Token Index: 836

Text #15

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.1351. Min Act: -0.1700

Data Index: 2384426 (Open Web Text)

Max Activating Token Index: 150

Text #16

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.1051. Min Act: -0.1700

Data Index: 6197693 (Open Web Text)

Max Activating Token Index: 212

Text #17

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.1226. Min Act: -0.1700

Data Index: 1130141 (Open Web Text)

Max Activating Token Index: 244

Text #18

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.1273. Min Act: -0.1700

Data Index: 1262215 (Open Web Text)

Max Activating Token Index: 517

Text #19

Max Range: 3.4306. Min Range: -3.4306

Max Act: 3.1128. Min Act: -0.1700

Data Index: 997858 (Open Web Text)

Max Activating Token Index: 845